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

    Neuronpedia

    INDEX
    Explanations

    instances of parentheses and related punctuation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    éal
    -0.20
    iggins
    -0.15
    asco
    -0.15
     Winds
    -0.15
    adio
    -0.15
    rades
    -0.15
    emark
    -0.15
    iff
    -0.15
    uida
    -0.15
    LOTS
    -0.14
    POSITIVE LOGITS
    деÑĢ
    0.14
    omba
    0.14
     dress
    0.14
    OCKET
    0.13
     Gun
    0.13
    nte
    0.13
    gro
    0.13
     groove
    0.13
    drivers
    0.13
    Ïħνα
    0.13
    Act Density 0.013%

    No Known Activations