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

    Neuronpedia

    INDEX
    Explanations

    numbers indicating age or quantity

    oai_token-act-pair · gpt-3.5-turbo

    references to demographics, attributes, or characteristics of subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Lear
    -0.65
    Untitled
    -0.61
    IPS
    -0.57
     experien
    -0.57
    ãĥĩãĤ£
    -0.57
    tnc
    -0.57
    Ble
    -0.55
    Module
    -0.54
    ELY
    -0.53
    UCT
    -0.53
    POSITIVE LOGITS
     meanwhile
    0.66
    ,
    0.58
     Marino
    0.56
     Edited
    0.54
     —
    0.54
     ,
    0.53
     roared
    0.52
    assetsadobe
    0.52
    utherford
    0.52
     Fallon
    0.52
    Act Density 1.034%

    No Known Activations