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

    Neuronpedia

    INDEX
    Explanations

    legal disclaimers and stipulations regarding responsibilities and limitations of liability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ThroughAttribute
    -0.57
    einander
    -0.57
    можно
    -0.55
    inafter
    -0.55
    MessageOf
    -0.55
    RenderAtEndOf
    -0.50
    entiary
    -0.49
    })]
    -0.49
    wreck
    -0.48
    ptid
    -0.48
    POSITIVE LOGITS
     directly
    0.56
    pompa
    0.54
     diret
    0.54
    (!__
    0.54
    Билгалдахарш
    0.53
    دانشنامهٔ
    0.53
    <bos>
    0.53
     виправивши
    0.53
    directly
    0.53
     Directly
    0.50
    Act Density 0.640%

    No Known Activations