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

    Neuronpedia

    INDEX
    Explanations

    adjectives and phrases indicating prominence or significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ов
    -0.13
    DOT
    -0.13
    lernen
    -0.13
    is
    -0.12
    etooth
    -0.12
     Recent
    -0.12
    á»ijn
    -0.12
    æĸ¹éĿ¢
    -0.12
    essler
    -0.12
    æľĢè¿ij
    -0.12
    POSITIVE LOGITS
    ly
    0.18
    -but
    0.17
    aneously
    0.17
    mente
    0.17
    /current
    0.16
    adele
    0.16
    -looking
    0.15
    -than
    0.15
    ised
    0.15
    -issue
    0.15
    Act Density 0.151%

    No Known Activations