© 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. 2232
    Prev
    Next
    INDEX
    Explanations

    phrases that express collective viewpoints or stances

    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
    obbies
    -0.79
    ortion
    -0.70
    tains
    -0.67
    ision
    -0.67
    ONSORED
    -0.66
    ographs
    -0.66
    ipal
    -0.65
    lund
    -0.64
    ays
    -0.63
    lights
    -0.63
    POSITIVE LOGITS
     owe
    1.11
    akening
    0.92
     need
    0.85
     salute
    0.84
     deserve
    0.82
     must
    0.80
     ought
    0.80
     hereby
    0.79
     guarantee
    0.78
     cannot
    0.77
    Activations Density 0.143%

    No Known Activations