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

    Neuronpedia

    INDEX
    Explanations

    names of organizations or positions

    oai_token-act-pair · gpt-3.5-turbo

    words related to organizations and their structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     DRAG
    -0.70
    utenberg
    -0.68
     Wink
    -0.68
     plent
    -0.66
     aster
    -0.65
     tremend
    -0.64
     Jiu
    -0.63
     drib
    -0.63
     prick
    -0.63
     Amph
    -0.63
    POSITIVE LOGITS
    ees
    1.18
    ment
    1.10
    ments
    1.05
    orship
    1.04
    iaries
    1.02
    rers
    1.01
    MENT
    0.99
    ients
    0.95
    ATIONAL
    0.93
    IAL
    0.93
    Act Density 0.139%

    No Known Activations