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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, particularly names and titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Bone
    -0.16
    anni
    -0.15
    aises
    -0.14
    tar
    -0.14
    relude
    -0.14
    ÑĢаб
    -0.14
    aise
    -0.13
    erais
    -0.13
    uper
    -0.13
     Frequ
    -0.13
    POSITIVE LOGITS
    tele
    0.17
    SWG
    0.15
     Wort
    0.15
    UTOR
    0.15
    raya
    0.15
    ombres
    0.14
    uggest
    0.14
    iblings
    0.14
    ãĥ»ãĥ»ãĥ»↵↵
    0.14
    ofday
    0.14
    Act Density 0.081%

    No Known Activations