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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a duration of time or continuity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     steel
    -0.14
     upon
    -0.14
    elix
    -0.14
     anh
    -0.14
     Hang
    -0.14
    roid
    -0.13
     ANSW
    -0.13
    éric
    -0.13
    den
    -0.13
     available
    -0.13
    POSITIVE LOGITS
    ancellor
    0.16
    era
    0.16
     ago
    0.16
    mî
    0.16
    enek
    0.15
    verty
    0.15
     Jeg
    0.15
    olon
    0.14
    ازÛĮ
    0.14
    oader
    0.14
    Act Density 0.013%

    No Known Activations