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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to names of places or titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iginal
    -0.16
    ary
    -0.16
    undo
    -0.15
    endo
    -0.15
    acific
    -0.15
    isci
    -0.15
    etwork
    -0.15
    lsru
    -0.15
    entarios
    -0.15
    odable
    -0.14
    POSITIVE LOGITS
    roe
    0.19
    FY
    0.16
    adora
    0.14
    alles
    0.14
     Rosenberg
    0.14
     synonyms
    0.14
    ÄĽÅ¾
    0.14
    roz
    0.14
    oin
    0.13
     FY
    0.13
    Act Density 0.063%

    No Known Activations