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

    Neuronpedia

    INDEX
    Explanations

    instances of punctuation marks and their context within sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ¸ãĥ¥
    -0.15
     latter
    -0.14
    åĶ
    -0.13
    strup
    -0.13
    ient
    -0.13
    /tos
    -0.13
    aille
    -0.13
     pack
    -0.13
    .mods
    -0.13
    acity
    -0.13
    POSITIVE LOGITS
    igu
    0.14
    ýš
    0.14
    Es
    0.14
    ipers
    0.14
    iped
    0.13
    hol
    0.13
    iani
    0.13
    ॰
    0.13
    igrant
    0.13
    ishi
    0.13
    Act Density 0.160%

    No Known Activations