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

    Neuronpedia

    INDEX
    Explanations

    eye

    np_max-act · gemini-2.0-flash

    descriptions of product features and specifications.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron fires on any occurrence of the word “eye” (including in compounds like “eye-catching,” “eye-popping,” or “eye-exercises”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    makt
    -0.08
    .fm
    -0.07
     parchment
    -0.07
     kennen
    -0.07
    format
    -0.07
    nergie
    -0.06
     tumult
    -0.06
     recomm
    -0.06
    Discussion
    -0.06
     restarting
    -0.06
    POSITIVE LOGITS
     Eye
    0.16
     Eyes
    0.14
     eye
    0.14
     eyes
    0.14
    Eye
    0.12
    eyes
    0.12
    -eye
    0.10
    eye
    0.10
     eyebrows
    0.09
    Ey
    0.09
    Act Density 0.021%

    No Known Activations