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

    Neuronpedia

    INDEX
    Explanations

    mentions of a range of options or variations in a context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abase
    -0.73
    orney
    -0.69
    stan
    -0.68
    reon
    -0.66
    ERSON
    -0.65
    IU
    -0.64
    robe
    -0.64
    thur
    -0.64
    abad
    -0.64
    stanbul
    -0.63
    POSITIVE LOGITS
     thereof
    0.87
    icult
    0.82
    ensical
    0.78
     Flavoring
    0.78
    istries
    0.73
     incarn
    0.72
     of
    0.71
     assortment
    0.69
    etting
    0.69
     distributions
    0.68
    Act Density 0.014%

    No Known Activations