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

    Neuronpedia

    INDEX
    Explanations

    references to user-generated content and discussions about themes in technology or software

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abay
    -0.16
    rish
    -0.16
    ibrator
    -0.15
    omi
    -0.14
    CESS
    -0.14
    guna
    -0.14
     Battles
    -0.14
    ëĵľë¦¬
    -0.14
    inou
    -0.13
    ovie
    -0.13
    POSITIVE LOGITS
     means
    0.18
     Levy
    0.16
    .fx
    0.14
     dint
    0.14
     vig
    0.14
     virtue
    0.14
    onya
    0.14
    лек
    0.13
     Garrison
    0.13
    arded
    0.13
    Act Density 0.537%

    No Known Activations