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

    Neuronpedia

    INDEX
    Explanations

    names of people or places

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific individuals or characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xual
    -0.79
    geist
    -0.70
     indicative
    -0.68
    cemic
    -0.65
     comparative
    -0.65
     crawl
    -0.65
    ergy
    -0.63
    HCR
    -0.63
     prevailing
    -0.62
    dose
    -0.62
    POSITIVE LOGITS
    ril
    1.13
    rolet
    0.93
    ota
    0.88
    arna
    0.88
    aji
    0.87
    rons
    0.87
    lov
    0.84
    atars
    0.84
    anas
    0.82
    iva
    0.81
    Act Density 0.008%

    No Known Activations