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

    Neuronpedia

    INDEX
    Explanations

    names containing the syllable "ul"

    oai_token-act-pair · gpt-3.5-turbo

    the prefix "ul" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Collider
    -0.61
     pleas
    -0.59
    PET
    -0.59
    OLD
    -0.58
     Hitman
    -0.58
     Cage
    -0.58
     Fellow
    -0.57
     Tables
    -0.55
     Clifford
    -0.55
     Feder
    -0.55
    POSITIVE LOGITS
    monary
    1.23
    terior
    1.05
    aiman
    1.01
    ibrary
    0.95
    ogy
    0.93
    itzer
    0.92
    iple
    0.92
    enium
    0.88
    anguage
    0.87
    gence
    0.87
    Act Density 0.042%

    No Known Activations