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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "good."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alers
    -0.18
    адÑĥ
    -0.16
    oley
    -0.15
    adero
    -0.15
    ville
    -0.15
     touched
    -0.15
     touch
    -0.15
    drs
    -0.15
    linger
    -0.15
     vag
    -0.14
    POSITIVE LOGITS
    tember
    0.16
    tons
    0.15
    //{{
    0.15
    ton
    0.15
    ector
    0.15
    ervo
    0.14
    utar
    0.14
    à¸łà¸²à¸¢à¹ĥà¸Ļ
    0.14
    avr
    0.14
    ÑĭÑĤ
    0.14
    Act Density 0.017%

    No Known Activations