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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and their frequency within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    \Mapping
    -0.16
     Ru
    -0.15
     grade
    -0.15
    edia
    -0.15
    Ø·
    -0.14
    isko
    -0.14
    HEL
    -0.14
    Äįil
    -0.14
    oks
    -0.13
    egl
    -0.13
    POSITIVE LOGITS
    agle
    0.18
    lane
    0.15
    urve
    0.14
    ãģĪ
    0.14
     ÑģооÑĤвеÑĤ
    0.14
    alette
    0.14
    oshi
    0.14
    oscope
    0.14
    ãĥ¼ãĥĵ
    0.14
    ãģĭãģĹ
    0.14
    Act Density 0.039%

    No Known Activations