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

    Neuronpedia

    INDEX
    Explanations

    expressions of personal favorites and preferences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abet
    -0.18
    latest
    -0.17
    YK
    -0.16
    IFO
    -0.15
    apy
    -0.15
    atti
    -0.15
    anson
    -0.14
     Resist
    -0.14
    ield
    -0.14
    uler
    -0.14
    POSITIVE LOGITS
     among
    0.18
    among
    0.17
     amongst
    0.17
     favorite
    0.17
     favourite
    0.15
    vÄĽÅĻ
    0.15
     Favorite
    0.15
    favorite
    0.14
    Among
    0.14
    elin
    0.14
    Act Density 0.072%

    No Known Activations