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

    Neuronpedia

    INDEX
    Explanations

    own

    np_max-act · gemini-2.0-flash

    Explanation of neuron 4 behavior: the main thing this neuron does is find personal and possessive pronouns (e.g. “his,” “own,” “our”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    legal terminology related to theft and punishment.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     وأن
    -0.06
     fazla
    -0.06
    作品
    -0.06
     Stad
    -0.06
     Baton
    -0.06
    etat
    -0.06
     přiz
    -0.06
    Drv
    -0.06
    励
    -0.06
     Goat
    -0.06
    POSITIVE LOGITS
    yc
    0.08
     foreground
    0.07
    eração
    0.06
    υμ
    0.06
    Bluetooth
    0.06
     reprint
    0.06
     disciplined
    0.06
     guarantees
    0.06
     uniforms
    0.06
    $↵
    0.06
    Act Density 0.000%

    No Known Activations