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

    Neuronpedia

    INDEX
    Explanations

    words related to established patterns or practices

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ileaks
    -0.85
    stocks
    -0.77
    gdala
    -0.76
    gow
    -0.74
    iaries
    -0.69
    obin
    -0.68
    entin
    -0.68
    kids
    -0.66
    ackets
    -0.65
    izoph
    -0.65
    POSITIVE LOGITS
    istically
    0.90
    istic
    0.86
     procedure
    0.81
     circumcision
    0.81
     slaughter
    0.80
    ALLY
    0.80
    ised
    0.78
    ized
    0.77
     performed
    0.75
     routine
    0.74
    Act Density 0.078%

    No Known Activations