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

    Neuronpedia

    INDEX
    Explanations

    references to specific articles or publications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    addy
    -0.21
    oor
    -0.16
    anax
    -0.16
    aktion
    -0.15
    rish
    -0.15
    anki
    -0.15
    aurus
    -0.15
    arkers
    -0.15
    ansa
    -0.14
    lder
    -0.14
    POSITIVE LOGITS
    zi
    0.22
    rey
    0.19
    iks
    0.18
    ignum
    0.17
    yer
    0.16
    sou
    0.16
    ogram
    0.16
    zy
    0.15
    ÃŃ
    0.15
    з
    0.15
    Act Density 0.030%

    No Known Activations