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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, particularly parentheses and brackets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dera
    -0.17
    cock
    -0.15
    Äįit
    -0.15
    ity
    -0.14
    steen
    -0.14
    ackle
    -0.14
    oux
    -0.14
     exactly
    -0.14
    EMON
    -0.13
    ruž
    -0.13
    POSITIVE LOGITS
    istrovstvÃŃ
    0.20
    undles
    0.15
    (#)
    0.15
    418
    0.14
    ecure
    0.14
    usk
    0.14
     Ruiz
    0.13
     thorough
    0.13
     Roses
    0.13
    hole
    0.13
    Act Density 0.007%

    No Known Activations