© 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. 2803
    Prev
    Next
    INDEX
    Explanations

    instances of the word "committed."

    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
    verty
    -0.81
    insula
    -0.76
    htaking
    -0.75
    irlf
    -0.75
    translation
    -0.73
    hibit
    -0.71
    regon
    -0.71
    yip
    -0.69
    bang
    -0.69
    Writing
    -0.68
    POSITIVE LOGITS
     until
    0.75
    until
    0.67
    Boo
    0.65
    ギ
    0.61
    iber
    0.61
     into
    0.60
     throughout
    0.58
     expires
    0.57
     UTC
    0.57
     longest
    0.57
    Activations Density 0.051%

    No Known Activations