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

    Neuronpedia

    INDEX
    Explanations

    references to abuse in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ellas
    -0.17
    ugg
    -0.14
    phia
    -0.14
    nic
    -0.14
    assic
    -0.14
    ÐĽÐIJ
    -0.13
     èij
    -0.13
    aldo
    -0.13
    oger
    -0.13
    raž
    -0.13
    POSITIVE LOGITS
    vu
    0.17
     Wich
    0.16
     Ink
    0.15
    acam
    0.15
    é¼»
    0.14
    ayar
    0.14
    leigh
    0.14
     Subject
    0.13
    amus
    0.13
    kul
    0.13
    Act Density 0.015%

    No Known Activations