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

    Neuronpedia

    INDEX
    Explanations

    statements asserting the existence or state of being

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OGND
    -0.88
     חיצוניים
    -0.77
     betweenstory
    -0.76
     TestBed
    -0.74
    ГЛА
    -0.66
    chord
    -0.66
    InjectAttribute
    -0.65
    fml
    -0.61
    __':
    -0.61
     متعلقه
    -0.61
    POSITIVE LOGITS
     the
    0.59
    requireNonNull
    0.54
     truly
    0.54
     an
    0.54
     sker
    0.53
     really
    0.53
    cosity
    0.51
    +#+#
    0.51
     real
    0.51
    miesz
    0.51
    Act Density 0.123%

    No Known Activations