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

    Neuronpedia

    INDEX
    Explanations

    references to outcomes or consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Goodman
    -0.15
    Ĥ
    -0.15
    inkel
    -0.14
    eron
    -0.14
    Injected
    -0.14
    ighton
    -0.13
     poison
    -0.13
    ermint
    -0.13
     thoroughly
    -0.13
    amar
    -0.13
    POSITIVE LOGITS
    antly
    0.20
    ãģ«ãģ¤
    0.17
    ToBounds
    0.16
    zte
    0.16
    hci
    0.16
    кеÑĤ
    0.15
    åĪĹ
    0.14
    ogui
    0.14
    èĥ
    0.14
    Ïĩα
    0.14
    Act Density 0.015%

    No Known Activations