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

    Neuronpedia

    INDEX
    Explanations

    adjectives describing emotions or qualities

    oai_token-act-pair · gpt-3.5-turbo

    expressions of personal opinion or evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rontal
    -0.67
     hemor
    -0.67
     coli
    -0.64
     downed
    -0.63
    mop
    -0.63
     boarded
    -0.62
    eties
    -0.60
    mercial
    -0.59
    raph
    -0.58
    ideon
    -0.57
    POSITIVE LOGITS
    SPONSORED
    0.86
    ?:
    0.83
     varies
    0.79
     differs
    0.78
     distinguishes
    0.72
     illustrates
    0.70
    Story
    0.67
     differed
    0.66
    requires
    0.66
     boils
    0.66
    Act Density 0.286%

    No Known Activations