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

    Neuronpedia

    INDEX
    Explanations

    references to specific local communities or organizations

    oai_token-act-pair · gpt-3.5-turbo

    references to local organizations or groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    issance
    -0.92
    sonian
    -0.88
    warts
    -0.81
    =-=-=-=-=-=-=-=-
    -0.76
    haar
    -0.74
    stroke
    -0.74
    ÙĴ
    -0.73
    pter
    -0.73
    furt
    -0.73
    å£
    -0.72
    POSITIVE LOGITS
     Local
    0.90
     Loc
    0.79
     Authorities
    0.72
     Authority
    0.69
    ization
    0.69
    izable
    0.69
     Supervisor
    0.69
     File
    0.66
     Coord
    0.66
     Forces
    0.66
    Act Density 0.019%

    No Known Activations