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

    Neuronpedia

    INDEX
    Explanations

    names of individuals or entities

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ACTED
    -0.87
    CHR
    -0.78
    senal
    -0.72
    PDATE
    -0.69
    ãĥ¼ãĥĨ
    -0.68
     à¨
    -0.67
     bulls
    -0.65
    OPLE
    -0.63
     conditioned
    -0.62
    expr
    -0.62
    POSITIVE LOGITS
    andowski
    1.47
    insky
    1.22
    inski
    1.00
    enstein
    0.99
    ield
    0.88
    die
    0.86
    omon
    0.85
    itsch
    0.84
    gren
    0.84
    iky
    0.84
    Act Density 0.016%

    No Known Activations