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

    Neuronpedia

    INDEX
    Explanations

    phrases discussing social issues and perceptions surrounding specific communities or topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    _EOF
    -0.16
    olen
    -0.16
    uman
    -0.15
    ako
    -0.15
    alette
    -0.15
    onia
    -0.15
    amas
    -0.14
    á»ı
    -0.14
    amma
    -0.14
    ugin
    -0.14
    POSITIVE LOGITS
    avian
    0.16
     unw
    0.15
    stants
    0.14
    .depend
    0.14
    ãĤ¦ãĤ§
    0.14
    593
    0.14
    VEC
    0.14
     reserved
    0.14
    viso
    0.14
    achts
    0.14
    Act Density 0.160%

    No Known Activations