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

    Neuronpedia

    INDEX
    Explanations

    terms related to binary data and code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ella
    -0.19
    lek
    -0.16
    avr
    -0.15
    lier
    -0.15
    leh
    -0.14
    tk
    -0.14
    iap
    -0.14
    av
    -0.14
    tok
    -0.14
    iko
    -0.14
    POSITIVE LOGITS
    arat
    0.17
    adele
    0.17
    ôn
    0.15
    -direction
    0.15
    hammer
    0.15
    ities
    0.15
    obl
    0.15
     Záp
    0.14
    illac
    0.14
    enal
    0.14
    Act Density 0.020%

    No Known Activations