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

    Neuronpedia

    INDEX
    Explanations

    references to social relationships and dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Lewis
    -0.16
    خط
    -0.15
    orre
    -0.15
    Lewis
    -0.15
    blr
    -0.15
     Zucker
    -0.15
    icorn
    -0.14
    izona
    -0.14
    ëĭ
    -0.14
    611
    -0.14
    POSITIVE LOGITS
    rette
    0.17
    ANNER
    0.15
    edir
    0.14
    uada
    0.14
    .tc
    0.14
    usercontent
    0.14
    uluk
    0.14
    óz
    0.14
     Ul
    0.14
    Specifier
    0.13
    Act Density 0.002%

    No Known Activations