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

    Neuronpedia

    INDEX
    Explanations

    occupations or titles of individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to character names or roles in narratives, particularly in a sports context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kaya
    -0.78
    achev
    -0.73
     tremend
    -0.72
    yip
    -0.69
    ovych
    -0.68
    uthor
    -0.68
     gobl
    -0.66
     Hels
    -0.66
     entitle
    -0.62
    oppable
    -0.61
    POSITIVE LOGITS
    aign
    0.84
    estial
    0.82
    xus
    0.74
     Blanc
    0.74
    enne
    0.71
    igham
    0.71
    ornia
    0.70
    Royal
    0.69
    ulhu
    0.68
    ioxide
    0.68
    Act Density 0.292%

    No Known Activations