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

    Neuronpedia

    INDEX
    Explanations

    phrases related to software or technical content

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     Stanley
    -0.62
     Trafford
    -0.59
    years
    -0.59
    court
    -0.58
     Boyle
    -0.56
    relations
    -0.56
     Kers
    -0.56
    ãĥĩãĤ£
    -0.54
     Remem
    -0.54
    USB
    -0.54
    POSITIVE LOGITS
    inki
    0.93
     reconcile
    0.74
    rouse
    0.72
    oby
    0.71
    fficient
    0.68
    oppable
    0.64
    velt
    0.64
    zzle
    0.64
     Survive
    0.63
     maximize
    0.63
    Act Density 0.299%

    No Known Activations