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

    Neuronpedia

    INDEX
    Explanations

    political and legal language

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Sard
    -0.68
    Mob
    -0.67
    qqa
    -0.67
    ãĤ´
    -0.66
    ned
    -0.66
    APD
    -0.66
    etary
    -0.65
    SourceFile
    -0.65
     Mechdragon
    -0.64
    ciples
    -0.63
    POSITIVE LOGITS
     uh
    1.08
     gasp
    0.98
     um
    0.94
    maybe
    0.81
     ah
    0.79
     yeah
    0.79
    wait
    0.79
    yeah
    0.79
    interrupted
    0.77
    look
    0.74
    Act Density 0.240%

    No Known Activations