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

    Neuronpedia

    INDEX
    Explanations

    references to verbal communication or speech

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Negative Logits
     lij
    -0.54
    Native
    -0.53
    ristol
    -0.52
    aral
    -0.52
     архивлан
    -0.52
    cerely
    -0.50
    yong
    -0.50
    tifical
    -0.50
     Bestimm
    -0.50
    inot
    -0.50
    POSITIVE LOGITS
     verbal
    3.23
     Verbal
    3.09
    Verbal
    2.95
     verbally
    2.91
    verbal
    2.77
    verb
    0.96
     nonverbal
    0.92
     Verb
    0.82
     verb
    0.80
     समीक्षक
    0.78
    Act Density 0.001%

    No Known Activations