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

    Neuronpedia

    INDEX
    Explanations

    concepts related to complex social dynamics and interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     so
    -0.43
     even
    -0.42
     and
    -0.41
     I
    -0.40
    ()):
    -0.40
    ()
    -0.39
     Sen
    -0.38
    fhir
    -0.38
     Fehl
    -0.37
     Kol
    -0.37
    POSITIVE LOGITS
     entanto
    1.02
    ftagPool
    0.97
     however
    0.93
     όμως
    0.92
     però
    0.90
    however
    0.89
     autorytatywna
    0.88
    ########.
    0.86
    Obrázky
    0.83
     فريبيس
    0.83
    Act Density 0.976%

    No Known Activations