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

    Neuronpedia

    INDEX
    Explanations

    programming constructs and syntax related to defining functions and methods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    The
    -0.43
    :
    -0.41
    「
    -0.41
    ...
    -0.39
     the
    -0.39
     either
    -0.39
    ,
    -0.38
    、「
    -0.38
     «
    -0.37
    『
    -0.37
    POSITIVE LOGITS
    ########.
    0.71
    &_
    0.67
    iſche
    0.60
    şört
    0.58
    &-
    0.57
     StringTokenizer
    0.55
     informée
    0.54
     թվական
    0.54
    schild
    0.54
    vacy
    0.53
    Act Density 0.760%

    No Known Activations