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

    Neuronpedia

    INDEX
    Explanations

    terms related to exceptions and exceptional qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ExecutionContext
    -0.16
    ume
    -0.15
    ι
    -0.14
    erno
    -0.14
    enticate
    -0.14
    gie
    -0.14
    inds
    -0.14
    indexed
    -0.14
    ge
    -0.14
    beth
    -0.14
    POSITIVE LOGITS
    ively
    0.21
    ally
    0.21
    ALLY
    0.20
    nal
    0.20
    ality
    0.20
    ities
    0.18
    nelle
    0.17
    /error
    0.17
    ordinary
    0.17
    antly
    0.16
    Act Density 0.038%

    No Known Activations