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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating levels or degrees of involvement or importance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uong
    -0.15
    Äįel
    -0.14
    анка
    -0.14
    kJ
    -0.14
    aja
    -0.14
    ::__
    -0.14
    OTES
    -0.14
    дам
    -0.14
    abin
    -0.14
    erin
    -0.13
    POSITIVE LOGITS
    arness
    0.15
    .lucene
    0.14
    flash
    0.14
    Flash
    0.13
    çiler
    0.13
    riends
    0.13
    innen
    0.13
    AVA
    0.13
    onaut
    0.13
    лÑıÑħ
    0.13
    Act Density 0.161%

    No Known Activations