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

    Neuronpedia

    INDEX
    Explanations

    references to equations in scientific or mathematical texts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    s
    -0.77
    ities
    -0.62
     Stö
    -0.60
    पया
    -0.59
     fű
    -0.59
    AnchorStyles
    -0.58
    InjectAttribute
    -0.57
    IF
    -0.56
    ses
    -0.56
    Bü
    -0.56
    POSITIVE LOGITS
    eqn
    1.59
     eqn
    1.10
    Eqn
    0.90
     Reforms
    0.82
    Fordítás
    0.81
    enoord
    0.77
    ykjav
    0.76
     صوتيه
    0.76
     wens
    0.76
     Gual
    0.74
    Act Density 0.001%

    No Known Activations