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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols and their associated contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Kenn
    -0.14
    apan
    -0.14
    KS
    -0.14
    ordo
    -0.14
    .tele
    -0.14
     Kral
    -0.13
    DMIN
    -0.13
     millenn
    -0.13
     ment
    -0.13
    ansk
    -0.13
    POSITIVE LOGITS
    reten
    0.16
    evin
    0.15
    mdi
    0.15
     pró
    0.14
     Bot
    0.14
    alion
    0.14
    Encoded
    0.14
    [class
    0.14
    pute
    0.14
    aida
    0.14
    Act Density 0.003%

    No Known Activations