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

    Neuronpedia

    INDEX
    Explanations

    numerical values, particularly dates and counts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    otton
    -0.15
    ifton
    -0.15
    onia
    -0.14
    arah
    -0.14
    ör
    -0.14
    oven
    -0.14
    orr
    -0.14
    ech
    -0.14
    ape
    -0.14
    ialog
    -0.13
    POSITIVE LOGITS
     ÙħÛĮÙĦادÛĮ
    0.16
    theid
    0.15
    buz
    0.14
    ë²Ħì§Ģ
    0.14
    imen
    0.14
    _regularizer
    0.14
    -vars
    0.14
    pollo
    0.13
    leck
    0.13
    berger
    0.13
    Act Density 0.013%

    No Known Activations