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

    Neuronpedia

    INDEX
    Explanations

    words related to speech and communication

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     richesse
    -0.64
     skydd
    -0.59
     ответственности
    -0.58
    ing
    -0.57
     culoare
    -0.56
     argint
    -0.56
     registrazione
    -0.56
    t
    -0.56
     Heere
    -0.55
     färg
    -0.55
    POSITIVE LOGITS
    Spoken
    1.14
     Spoken
    1.13
     spoken
    1.04
    spoken
    0.97
     للاسماء
    0.88
     `<
    0.85
     Monta
    0.81
    )</
    0.80
    poken
    0.78
    cipital
    0.77
    Act Density 0.001%

    No Known Activations