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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to a specific place or character named "Ras"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific geographical or proper names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ancial
    -0.78
    sylvania
    -0.77
    ItemTracker
    -0.75
    culosis
    -0.75
     Drift
    -0.73
    Reviewer
    -0.72
    sburgh
    -0.71
    ATA
    -0.67
    fare
    -0.64
     Grimes
    -0.62
    POSITIVE LOGITS
    semble
    1.07
    pect
    0.96
    bian
    0.93
    ync
    0.92
    coe
    0.89
    quez
    0.87
    xual
    0.86
    ques
    0.85
     Jas
    0.84
     Ras
    0.82
    Act Density 0.011%

    No Known Activations