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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, specifically names of people and places

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     repe
    -0.16
    ModuleName
    -0.15
    untas
    -0.15
    ined
    -0.15
    Ĺ
    -0.15
    uffs
    -0.14
    åĪĢ
    -0.14
    Kick
    -0.14
    çĴ
    -0.14
    ears
    -0.14
    POSITIVE LOGITS
     Silence
    0.16
     Fame
    0.16
    gii
    0.14
    /archive
    0.14
    leaf
    0.14
    ÏİÏĤ
    0.14
     Salvador
    0.13
     SPDX
    0.13
    -motion
    0.13
     Wheeler
    0.13
    Act Density 0.114%

    No Known Activations