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

    Neuronpedia

    INDEX
    Explanations

    words related to people's names and titles

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific names or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Publisher
    -0.75
    washer
    -0.71
    ModLoader
    -0.69
    pread
    -0.68
    ħĭ
    -0.66
    Phill
    -0.65
    riad
    -0.63
    wallet
    -0.62
     pardon
    -0.61
    mble
    -0.61
    POSITIVE LOGITS
    uation
    1.20
    uations
    1.11
    uated
    1.03
    uate
    1.02
    uating
    1.01
    uates
    0.98
    uable
    0.88
    anche
    0.87
    onge
    0.87
    arial
    0.83
    Act Density 0.011%

    No Known Activations