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

    Neuronpedia

    INDEX
    Explanations

    occurrences of parentheses and related symbols in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     $+
    -0.58
     \&
    -0.56
    она
    -0.52
    ál
    -0.51
    Ctor
    -0.50
    []);
    -0.50
     Ob
    -0.49
    estad
    -0.49
    [];
    -0.49
    "]["
    -0.49
    POSITIVE LOGITS
    setVerticalGroup
    0.95
     useAppContext
    0.86
     ProtoMessage
    0.82
    الإنجليزية
    0.77
    شهاد
    0.77
     '\\;'
    0.76
     semej
    0.76
    InjectAttribute
    0.75
    __':
    0.75
    matchCondition
    0.74
    Act Density 0.088%

    No Known Activations