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

    Neuronpedia

    INDEX
    Explanations

    quotes and references to classic literature

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ypo
    -0.17
     дол
    -0.17
    agr
    -0.16
    urer
    -0.15
    opper
    -0.15
    aub
    -0.15
    anko
    -0.14
     Shore
    -0.14
    ucc
    -0.14
    777
    -0.14
    POSITIVE LOGITS
     Hed
    0.17
     Bunny
    0.16
    anford
    0.16
    SENS
    0.16
    roman
    0.15
    etten
    0.14
    <quote
    0.14
    ecz
    0.14
     moderne
    0.14
     Bench
    0.14
    Act Density 0.002%

    No Known Activations