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

    Neuronpedia

    INDEX
    Explanations

    assertions and hypotheses related to mathematical proofs or logical reasoning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vician
    -0.67
    انيف
    -0.66
    atrician
    -0.60
    continence
    -0.60
    ositol
    -0.59
     chon
    -0.59
    manteau
    -0.57
    noons
    -0.57
    новниш
    -0.56
    writeFieldEnd
    -0.56
    POSITIVE LOGITS
     can
    0.96
     fácilmente
    0.82
    Can
    0.80
     Can
    0.79
     facilmente
    0.78
     facilement
    0.77
    can
    0.76
     easily
    0.71
    bitField
    0.68
    也可以
    0.67
    Act Density 1.172%

    No Known Activations