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

    Neuronpedia

    INDEX
    Explanations

    mathematical variables and their relationships in formulas

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    e
    -0.09
    p
    -0.08
    c
    -0.08
    iversal
    -0.08
    r
    -0.07
    i
    -0.07
    -worthy
    -0.07
    ueva
    -0.07
    it
    -0.07
    hift
    -0.07
    POSITIVE LOGITS
    /her
    0.10
    955
    0.07
     průbÄĽhu
    0.07
    ses
    0.07
    anus
    0.07
    imesteps
    0.06
    üzel
    0.06
    _tF
    0.06
    esco
    0.06
    ERTICAL
    0.06
    Act Density 2.486%

    No Known Activations