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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks or phrases indicating a conditional or introductory statement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .
    -0.56
     culturelle
    -0.55
    utro
    -0.45
    giacca
    -0.44
    Namaste
    -0.43
    itou
    -0.42
    izade
    -0.42
     dolgo
    -0.42
    ikti
    -0.42
    Geografi
    -0.41
    POSITIVE LOGITS
    PreferredItem
    0.95
    enumii
    0.85
     Roskov
    0.85
    OGND
    0.81
    GeneratedValue
    0.80
    GIVEREF
    0.77
     للاسماء
    0.77
    SPATH
    0.76
    CppCodeGen
    0.76
    BufferException
    0.75
    Act Density 0.165%

    No Known Activations