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

    Neuronpedia

    INDEX
    Explanations

    repeated phrases or conjunctions indicating emphasis or inclusion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    igham
    -0.17
    atron
    -0.16
    slu
    -0.16
    omnia
    -0.15
     ла
    -0.15
    iani
    -0.15
    idden
    -0.15
    è¦Ĩ
    -0.14
     GLenum
    -0.14
     ìłĦìļ©
    -0.14
    POSITIVE LOGITS
     subt
    0.16
    utor
    0.16
     Harm
    0.15
    .Platform
    0.14
    plat
    0.14
    zen
    0.14
    246
    0.14
    228
    0.14
     palm
    0.14
     Nad
    0.13
    Act Density 0.000%

    No Known Activations