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

    Neuronpedia

    INDEX
    Explanations

    statements related to evidence or demonstration of results

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     witness
    -0.44
    find
    -0.43
     contrary
    -0.39
    ॉग
    -0.39
    坎
    -0.38
    Witness
    -0.38
     vodou
    -0.38
     can
    -0.38
    can
    -0.38
    気が
    -0.37
    POSITIVE LOGITS
    expandindo
    1.13
    abestanden
    1.13
    Diweddarwch
    0.95
    RTLR
    0.91
     referenties
    0.90
    تقاوى
    0.89
     AssemblyCulture
    0.85
    Personendaten
    0.84
    twimg
    0.83
     calendriers
    0.81
    Act Density 0.049%

    No Known Activations