Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references to influential or distinguished individuals

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with distinguished individuals and social etiquette

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ython
    -0.77
     Bombs
    -0.75
     Triumph
    -0.75
    opia
    -0.75
    opian
    -0.74
     addon
    -0.73
    pring
    -0.71
    inka
    -0.71
    ondo
    -0.69
     Typ
    -0.69
    POSITIVE LOGITS
     eminent
    2.91
     cour
    2.19
    minent
    1.55
     hail
    1.51
     solicit
    1.45
     taxation
    1.12
     condemnation
    1.06
     landowners
    1.03
     solic
    0.98
    cour
    0.97
    Act Density 0.049%

    No Known Activations