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

    Neuronpedia

    INDEX
    Explanations

    punctuation, specifically commas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ervices
    -0.14
    ettes
    -0.14
    acle
    -0.14
    else
    -0.13
    umbles
    -0.13
    itor
    -0.13
    uya
    -0.13
    غ
    -0.13
    eba
    -0.13
    une
    -0.13
    POSITIVE LOGITS
    inar
    0.15
    emek
    0.14
    'gc
    0.14
    AndPassword
    0.13
    иÑĢ
    0.13
     Creature
    0.13
    ÑĪиб
    0.13
    Pages
    0.13
     it
    0.13
    esimal
    0.13
    Act Density 0.181%

    No Known Activations