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

    Neuronpedia

    INDEX
    Explanations

    conditional phrases and expressions that suggest skepticism or doubt

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    The
    -0.73
    .
    -0.66
    ↵↵
    -0.54
    。
    -0.48
    Other
    -0.46
    λίου
    -0.46
    ;
    -0.46
     the
    -0.45
     Emits
    -0.43
     The
    -0.43
    POSITIVE LOGITS
    تقاوى
    1.03
     Мексичка
    1.01
     виправивши
    0.94
     صوتيه
    0.86
    وأضاف
    0.81
    expandindo
    0.79
     يتيمه
    0.76
    LookAnd
    0.75
     gynhyrchwyd
    0.73
     мәкал
    0.72
    Act Density 1.952%

    No Known Activations