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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating change, innovation, or significant events

    oai_token-act-pair · gpt-3.5-turbo

    statements asserting existence or occurrence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    powers
    -0.71
    uum
    -0.71
    agues
    -0.65
    perate
    -0.64
    ishly
    -0.63
    Except
    -0.63
    ull
    -0.62
    ventures
    -0.60
    fuck
    -0.60
    essor
    -0.59
    POSITIVE LOGITS
     undoubtedly
    0.87
     evidenced
    0.73
     how
    0.71
    ometric
    0.71
     whether
    0.69
     doubtless
    0.69
     afforded
    0.66
     namely
    0.65
     that
    0.64
     termed
    0.64
    Act Density 0.149%

    No Known Activations