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

    Neuronpedia

    INDEX
    Explanations

    references to a specific pattern or code of characters, specifically 'E9' or 'E10'

    oai_token-act-pair · gpt-3.5-turbo

    instances of a specific letter or character pattern related to "E"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ifier
    -0.88
    runners
    -0.87
    ifiers
    -0.84
    ification
    -0.84
    ifications
    -0.82
    amaz
    -0.79
    lime
    -0.75
    ifying
    -0.75
    ifiable
    -0.74
    essed
    -0.74
    POSITIVE LOGITS
    LECT
    1.35
    OPLE
    1.14
    ASY
    1.13
    AST
    1.03
    fficient
    1.02
    instein
    1.00
    lements
    1.00
    ternity
    0.97
    FAULT
    0.91
    FI
    0.91
    Act Density 0.041%

    No Known Activations