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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks that could indicate rhetorical or conversational elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    owell
    -0.15
     Bullet
    -0.14
     Reform
    -0.14
     Salon
    -0.14
    ãģıãĤĮ
    -0.14
    以为
    -0.14
    AVIS
    -0.14
    abelle
    -0.14
    ullet
    -0.14
    _Flag
    -0.14
    POSITIVE LOGITS
    enton
    0.15
    alsa
    0.15
    Disappear
    0.15
    eger
    0.15
    agnar
    0.15
    rı
    0.14
    elsen
    0.13
    unpack
    0.13
    Ign
    0.13
    onder
    0.13
    Act Density 0.322%

    No Known Activations