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

    Neuronpedia

    INDEX
    Explanations

    lines or segments of code or data followed by numerical values or parameters

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     EconPapers
    -0.84
    #+#
    -0.79
    anskje
    -0.78
    Hochspringen
    -0.78
    Tikang
    -0.77
    bibinfo
    -0.73
     للمعارف
    -0.72
    stdc
    -0.71
     referenties
    -0.71
     surla
    -0.69
    POSITIVE LOGITS
     Spirituality
    0.43
     stron
    0.43
    ρυ
    0.42
     kling
    0.41
     trefoil
    0.41
    ်း
    0.40
     verg
    0.40
     sva
    0.40
     HOSPITAL
    0.40
     tica
    0.39
    Act Density 0.001%

    No Known Activations