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

    Neuronpedia

    INDEX
    Explanations

    words and phrases that express uncertainty or qualify assertions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    riterion
    -0.15
     Belt
    -0.14
    erea
    -0.14
    tp
    -0.13
    asher
    -0.13
     Ful
    -0.13
    æ
    -0.13
    ilingual
    -0.13
    ÑĢеп
    -0.13
    ighton
    -0.13
    POSITIVE LOGITS
    onga
    0.15
    eral
    0.15
    "crypto
    0.14
    ija
    0.14
    Hdr
    0.14
    iju
    0.14
    辺
    0.14
    igo
    0.14
    kel
    0.14
    .bn
    0.14
    Act Density 0.001%

    No Known Activations