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

    Neuronpedia

    INDEX
    Explanations

    instances of punctuation, particularly commas, indicating a focus on sentence structure or breaks in thought

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ulas
    -0.15
    γγ
    -0.15
    elm
    -0.15
    intr
    -0.14
    anoi
    -0.14
    avanaugh
    -0.14
    akh
    -0.14
     Uz
    -0.14
    ula
    -0.14
    otherwise
    -0.14
    POSITIVE LOGITS
    ibre
    0.17
    ency
    0.15
    ulle
    0.14
    late
    0.14
    459
    0.14
    avery
    0.13
     Hod
    0.13
     Ñħол
    0.13
    Cpp
    0.13
    ìĨĶ
    0.13
    Act Density 0.048%

    No Known Activations