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

    Neuronpedia

    INDEX
    Explanations

    lines of code related to reading input values

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Negative Logits
    OGND
    -0.87
    Sucesor
    -0.87
    upaten
    -0.78
     بيها
    -0.77
    RTEE
    -0.71
    rungsseite
    -0.69
    ьаж
    -0.69
     CreateTagHelper
    -0.68
    FilterChain
    -0.66
     defaultstate
    -0.66
    POSITIVE LOGITS
    cin
    1.89
    CIN
    0.75
    cinta
    0.55
     finais
    0.55
    spectos
    0.54
     referenties
    0.52
     verste
    0.50
    Comentarios
    0.49
     esperan
    0.49
     Comentarios
    0.47
    Act Density 0.001%

    No Known Activations