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

    Neuronpedia

    INDEX
    Explanations

    mentions of a specific location named "McAlester"

    oai_token-act-pair · gpt-3.5-turbo

    unique or special characters within text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DragonMagazine
    -0.86
    espie
    -0.84
     externalToEVAOnly
    -0.81
     Gillespie
    -0.77
    aults
    -0.72
     Jenner
    -0.72
    istics
    -0.71
     Siren
    -0.71
     Tid
    -0.70
     WARN
    -0.70
    POSITIVE LOGITS
    ĥ
    1.33
    á
    1.32
    ķ
    1.29
    ¼
    1.26
    ´
    1.25
    ĵĺ
    1.25
    Ķ
    1.15
    º
    1.14
    1.13
    IJ
    1.13
    Act Density 0.004%

    No Known Activations