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

    Neuronpedia

    INDEX
    Explanations

    keywords related to data privacy and government access

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to direct access and involvement in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     vert
    -0.66
     cabbage
    -0.66
     scraps
    -0.65
     brightest
    -0.65
     Carbuncle
    -0.64
    flies
    -0.63
     worms
    -0.63
    times
    -0.63
     neglig
    -0.61
    uly
    -0.61
    POSITIVE LOGITS
    idad
    0.79
    IDA
    0.77
    achable
    0.75
    SpaceEngineers
    0.73
    ctive
    0.73
    UGC
    0.73
    PsyNetMessage
    0.71
    abal
    0.70
    iration
    0.69
    ucl
    0.68
    Act Density 0.237%

    No Known Activations