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

    Neuronpedia

    INDEX
    Explanations

    common nouns and pronouns indicating possession or relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Demp
    -0.16
    SCO
    -0.15
    tuk
    -0.15
    û
    -0.15
     Prev
    -0.14
    ostel
    -0.14
    _attachments
    -0.14
    OLA
    -0.14
    COPE
    -0.14
    æIJŃ
    -0.14
    POSITIVE LOGITS
    acket
    0.16
     ber
    0.15
    ACKET
    0.15
    chet
    0.15
     gall
    0.14
    ervlet
    0.14
    rawn
    0.14
    igli
    0.14
    uso
    0.14
    iform
    0.14
    Act Density 0.001%

    No Known Activations