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

    Neuronpedia

    INDEX
    Explanations

    instances of brackets and punctuation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /
    -0.54
    :
    -0.52
    ・
    -0.52
     /
    -0.45
     D
    -0.43
    様な
    -0.43
    ;
    -0.42
    ,
    -0.42
    стра
    -0.42
    argent
    -0.41
    POSITIVE LOGITS
     and
    1.64
     etc
    1.20
     그리고
    1.12
    그리고
    1.09
     ועוד
    1.04
    そして
    0.98
    etc
    0.94
    reszcie
    0.92
     usw
    0.91
     Etc
    0.91
    Act Density 0.568%

    No Known Activations