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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating expectations or conditions regarding social interactions and obligations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    quam
    -0.15
    ewe
    -0.15
     Dial
    -0.15
    QUI
    -0.14
    reesome
    -0.14
    portion
    -0.14
    elay
    -0.14
    inho
    -0.14
    heads
    -0.14
    adder
    -0.13
    POSITIVE LOGITS
    ura
    0.16
     addCriterion
    0.15
    enda
    0.15
    ź
    0.15
    _stub
    0.15
    lem
    0.15
    ritz
    0.14
    acz
    0.14
    nda
    0.14
    vard
    0.14
    Act Density 0.009%

    No Known Activations