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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks at the end of statements or commands in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     dezelve
    -0.80
     desmotivaciones
    -0.79
     zijne
    -0.76
     zoude
    -0.72
    hésite
    -0.71
     queſta
    -0.71
     ainfi
    -0.70
     miniaturka
    -0.70
     المعيارى
    -0.69
     affari
    -0.68
    POSITIVE LOGITS
    ;
    1.37
    ,
    0.80
    ;
    0.75
    :
    0.69
    .
    0.66
    <bos>
    0.57
     to
    0.55
     and
    0.55
     for
    0.53
    !
    0.53
    Act Density 0.457%

    No Known Activations