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

    Neuronpedia

    INDEX
    Explanations

    command lines or code snippets

    oai_token-act-pair · gpt-3.5-turbo

    instances of punctuation marks and their associated delimiters in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ega
    -0.79
    entimes
    -0.76
    conom
    -0.73
    itational
    -0.73
    avorite
    -0.72
    ovie
    -0.69
    everal
    -0.68
    akia
    -0.67
     conclud
    -0.66
    ucks
    -0.65
    POSITIVE LOGITS
     "\
    0.88
     etc
    0.84
     lambda
    0.82
     /*
    0.80
     uint
    0.77
     sizeof
    0.75
    ioch
    0.74
     Vector
    0.74
     partName
    0.73
     //
    0.71
    Act Density 0.055%

    No Known Activations