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

    Neuronpedia

    INDEX
    Explanations

    numerical values or references, particularly related to statistics or data points

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    ushin
    -0.82
    twimg
    -0.71
    帖最后由
    -0.71
     setContent
    -0.69
     depth
    -0.68
    Datuak
    -0.68
     Depth
    -0.67
     Bü
    -0.66
    EClass
    -0.66
    ادث
    -0.66
    POSITIVE LOGITS
    ArgsConstructor
    0.74
     Lear
    0.71
     Marr
    0.69
     Vega
    0.69
    cetin
    0.68
     Martel
    0.66
     Warne
    0.65
    szön
    0.64
     Martine
    0.64
    ậc
    0.64
    Act Density 0.378%

    No Known Activations