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

    Neuronpedia

    INDEX
    Explanations

    names and proper nouns associated with individuals and entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    chant
    -0.16
    ariat
    -0.16
    obuf
    -0.16
    yte
    -0.15
    lexer
    -0.15
    cano
    -0.15
    orida
    -0.14
    luv
    -0.14
     Horizontal
    -0.14
    代
    -0.14
    POSITIVE LOGITS
    azon
    0.17
    izons
    0.17
    izon
    0.17
     popcorn
    0.14
    ilitation
    0.14
    oldt
    0.14
    estr
    0.14
    Realm
    0.14
     Vance
    0.14
    ullan
    0.14
    Act Density 0.092%

    No Known Activations