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

    Neuronpedia

    INDEX
    Explanations

    titles or names associated with significant roles or categories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Äijoạn
    -0.15
    forder
    -0.15
    reeze
    -0.14
    hea
    -0.14
    heck
    -0.14
     Loft
    -0.14
    arer
    -0.14
    fal
    -0.13
     sublic
    -0.13
    æ¯
    -0.13
    POSITIVE LOGITS
     into
    0.20
     time
    0.19
     get
    0.17
     another
    0.17
     out
    0.17
     going
    0.17
     big
    0.17
     not
    0.17
     getting
    0.16
     eyes
    0.16
    Act Density 0.165%

    No Known Activations