© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 1568
    Prev
    Next
    INDEX
    Explanations

    instances of the phrase "in" indicating involvement or presence in various scenarios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    �
    -0.78
    VERTISEMENT
    -0.78
    isSpecialOrderable
    -0.76
     Photograph
    -0.73
    cia
    -0.72
    selves
    -0.72
    anwhile
    -0.70
    nell
    -0.70
    ONSORED
    -0.69
    umbered
    -0.69
    POSITIVE LOGITS
    Change
    0.67
    replace
    0.66
     hiber
    0.66
     rapid
    0.66
     eclipse
    0.66
     termination
    0.64
    Conf
    0.63
     collisions
    0.63
     bal
    0.63
     separation
    0.62
    Activations Density 0.083%

    No Known Activations