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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate authorship or attribution related to actions or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     houſe
    -0.78
     itſelf
    -0.76
     calvin
    -0.74
     Reſ
    -0.72
     purpoſe
    -0.70
     Chriftian
    -0.70
     zealand
    -0.68
     Oedipus
    -0.68
     Anſ
    -0.67
     Oilers
    -0.67
    POSITIVE LOGITS
     BY
    1.52
     by
    1.44
     By
    1.30
     oleh
    1.27
    by
    1.26
     Byers
    1.26
    BY
    1.19
    By
    1.17
    filterBy
    1.14
    selectBy
    1.10
    Act Density 0.401%

    No Known Activations