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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating collaboration and partnerships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nist
    -0.15
    onn
    -0.15
    nex
    -0.15
    åĿĬ
    -0.15
     nav
    -0.14
     Shay
    -0.14
    _TRACE
    -0.14
    925
    -0.14
     Sokol
    -0.14
    nav
    -0.14
    POSITIVE LOGITS
     Bellev
    0.17
    pa
    0.17
    sd
    0.15
    tea
    0.15
    ARS
    0.15
    inou
    0.14
    _pa
    0.14
     Pa
    0.14
     pa
    0.14
    SD
    0.14
    Act Density 0.038%

    No Known Activations