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

    Neuronpedia

    INDEX
    Explanations

    references to new research findings and studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    assi
    -0.16
    ander
    -0.16
    ust
    -0.15
    sel
    -0.15
    usto
    -0.14
    udio
    -0.14
     Lap
    -0.14
    ç½²
    -0.14
    ze
    -0.14
    yster
    -0.14
    POSITIVE LOGITS
    efon
    0.17
    ledon
    0.16
     milfs
    0.15
    hyth
    0.15
    wargs
    0.14
    idar
    0.14
     feeding
    0.14
    OTTOM
    0.14
    onas
    0.14
    .Uint
    0.14
    Act Density 0.080%

    No Known Activations