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

    Neuronpedia

    INDEX
    Explanations

    dates, years, and titles with names

    oai_token-act-pair · gpt-3.5-turbo

    mentions of individuals being recognized or awarded in sports contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rums
    -0.73
    ecd
    -0.72
    olen
    -0.71
     lies
    -0.70
    raph
    -0.68
    eat
    -0.67
    heres
    -0.66
    isks
    -0.65
     webs
    -0.64
    ranging
    -0.64
    POSITIVE LOGITS
     honorary
    0.84
     prestigious
    0.81
     waivers
    0.75
    ç·
    0.72
    èĢħ
    0.71
     Celebrity
    0.71
    åĤ
    0.68
     eligible
    0.68
    ij士
    0.66
     ministerial
    0.66
    Act Density 0.222%

    No Known Activations