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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, particularly periods and commas, indicating sentence structure and flow

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    TION
    -0.16
    ardy
    -0.15
    ager
    -0.15
    符
    -0.15
    -REAL
    -0.14
    ahn
    -0.14
    òa
    -0.14
    loven
    -0.14
     htons
    -0.14
    edor
    -0.13
    POSITIVE LOGITS
    eel
    0.16
    aklı
    0.14
    ACHE
    0.14
     rais
    0.14
    hod
    0.14
    rais
    0.14
    e
    0.14
    zin
    0.14
    aura
    0.14
     reg
    0.14
    Act Density 0.061%

    No Known Activations