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

    Neuronpedia

    INDEX
    Explanations

    words related to hosting and nurturing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Å¡et
    -0.17
    erb
    -0.15
    uter
    -0.15
    ileged
    -0.15
     McA
    -0.15
    ceil
    -0.15
    ewolf
    -0.14
    unday
    -0.14
    adla
    -0.14
     Dynam
    -0.14
    POSITIVE LOGITS
    ela
    0.16
     dim
    0.16
    дÑĢеÑģ
    0.15
    ym
    0.15
    ancy
    0.15
    Substring
    0.15
    _controls
    0.14
    776
    0.14
     Ent
    0.14
    лаз
    0.14
    Act Density 0.017%

    No Known Activations