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

    Neuronpedia

    INDEX
    Explanations

    names and terms related to technology and sports figures

    oai_token-act-pair · gpt-3.5-turbo

    mentions of names or terms related to individuals and specific actions, particularly in contexts of recognition or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    =#
    -0.75
     Quarterly
    -0.73
    ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
    -0.73
    sburgh
    -0.71
     anesthesia
    -0.68
     Genie
    -0.64
    sburg
    -0.64
     Orion
    -0.64
    Ö¼
    -0.63
    creen
    -0.63
    POSITIVE LOGITS
    azar
    0.87
     Bam
    0.85
     Ub
    0.81
    yssey
    0.78
    wered
    0.77
    odied
    0.77
    aughs
    0.75
    untu
    0.75
    icts
    0.75
    uran
    0.73
    Act Density 0.016%

    No Known Activations