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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and numbers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Dispatcher
    -0.15
    imore
    -0.14
    Mahon
    -0.14
    adle
    -0.14
    adies
    -0.14
    enant
    -0.14
     reg
    -0.14
     Schiff
    -0.14
    tridge
    -0.14
    aving
    -0.14
    POSITIVE LOGITS
    abstract
    0.28
     abstract
    0.27
    .abstract
    0.20
     Abstract
    0.20
    _abstract
    0.19
    _Abstract
    0.18
    bstract
    0.17
    Abstract
    0.17
    STRACT
    0.17
    .Abstract
    0.17
    Act Density 0.004%

    No Known Activations