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

    Neuronpedia

    INDEX
    Explanations

    words related to events, actions, and their consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anton
    -0.16
    ecure
    -0.16
    ANNER
    -0.15
    ombo
    -0.15
    ÄĽst
    -0.15
    ache
    -0.15
    haar
    -0.14
    ìŀij
    -0.14
    vrier
    -0.14
    بش
    -0.14
    POSITIVE LOGITS
    873
    0.15
    bij
    0.15
     Din
    0.14
    olest
    0.14
    apult
    0.14
     xlink
    0.14
    泡
    0.14
     Worlds
    0.14
    441
    0.14
     chez
    0.13
    Act Density 0.002%

    No Known Activations