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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, particularly parentheses and periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kees
    -0.17
    anca
    -0.17
    stit
    -0.14
    allocated
    -0.14
     Grat
    -0.14
    åħ¹
    -0.14
     McCart
    -0.14
    loff
    -0.14
    Ñīи
    -0.14
    reak
    -0.13
    POSITIVE LOGITS
    amaz
    0.15
    erdem
    0.15
    ahat
    0.15
    imary
    0.14
    )null
    0.14
    ect
    0.14
    ÙģÙĩÙĪÙħ
    0.14
    hazi
    0.14
    folk
    0.14
    ãĥĭãĥ¼
    0.14
    Act Density 0.010%

    No Known Activations