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

    Neuronpedia

    INDEX
    Explanations

    terms related to specific sectors or fields

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    ableness
    -0.82
     McLaughlin
    -0.80
     Giz
    -0.79
    tabak
    -0.78
     Dn
    -0.77
     Wrang
    -0.77
    ніципалі
    -0.77
    ]='\
    -0.77
     Appropriation
    -0.75
     Pli
    -0.73
    POSITIVE LOGITS
     SECTOR
    1.47
     Sector
    1.35
     sectors
    1.30
     sector
    1.28
    SECTOR
    1.27
     Sectors
    1.23
    Sector
    1.20
    sector
    1.14
    sectors
    1.11
    Sectors
    1.04
    Act Density 0.004%

    No Known Activations