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

    Neuronpedia

    INDEX
    Explanations

    terms related to outcomes or consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ila
    -0.18
    lad
    -0.15
    ighton
    -0.14
    Injected
    -0.14
    ie
    -0.14
    esta
    -0.14
    EventManager
    -0.14
    assed
    -0.14
     Goodman
    -0.14
    se
    -0.13
    POSITIVE LOGITS
    antly
    0.19
    hci
    0.19
    eer
    0.17
    кеÑĤ
    0.16
    zte
    0.16
    ãģ«ãģ¤
    0.16
    Ïĩα
    0.16
     into
    0.15
    ogui
    0.15
    озÑı
    0.15
    Act Density 0.016%

    No Known Activations