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

    Neuronpedia

    INDEX
    Explanations

    references to manuals or technical documentation

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of manuals and diagnostic tools

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    venge
    -0.71
    bucks
    -0.70
    orate
    -0.69
    cffff
    -0.69
    cedented
    -0.68
    ments
    -0.67
     Canary
    -0.65
    timeout
    -0.65
    ĪĴ
    -0.65
    paren
    -0.65
    POSITIVE LOGITS
     manuscript
    0.92
     vit
    0.91
     detailing
    0.91
     pages
    0.89
     edition
    0.89
     outlining
    0.89
     editors
    0.88
     entries
    0.86
     booklet
    0.86
     entry
    0.84
    Act Density 0.098%

    No Known Activations