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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and colons in code snippets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ants
    -0.16
    zel
    -0.15
     Sask
    -0.15
    ãģ¨ãģĨ
    -0.15
    agar
    -0.14
    ãĤ¥
    -0.14
     Dek
    -0.14
    olon
    -0.14
    ickle
    -0.14
     fore
    -0.14
    POSITIVE LOGITS
    arton
    0.18
    ooter
    0.17
    rium
    0.16
    undle
    0.16
    ElapsedTime
    0.14
    uese
    0.14
    istani
    0.14
    omik
    0.14
    hardt
    0.14
    ÑĪÑĤ
    0.14
    Act Density 0.007%

    No Known Activations