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

    Neuronpedia

    INDEX
    Explanations

    references to authors or creators of works

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Wich
    -0.17
    iddet
    -0.16
    azzi
    -0.15
    rál
    -0.15
    apot
    -0.15
    rve
    -0.15
    anki
    -0.15
    äºĪ
    -0.15
    liers
    -0.14
    rug
    -0.14
    POSITIVE LOGITS
    usk
    0.16
    icz
    0.15
    amber
    0.15
    une
    0.15
    dan
    0.14
    εβ
    0.14
     manuals
    0.14
     vitae
    0.14
    ê¹
    0.14
    dad
    0.14
    Act Density 0.004%

    No Known Activations