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

    Neuronpedia

    INDEX
    Explanations

    proper nouns with initials, particularly those that are abbreviated with periods like "a.k.a"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the letter 'k'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iled
    -0.69
    rawdownloadcloneembedreportprint
    -0.64
    interstitial
    -0.63
    ãĥĥãĥī
    -0.59
    UU
    -0.58
    etter
    -0.58
    quist
    -0.58
    arial
    -0.57
    riott
    -0.57
    SPA
    -0.57
    POSITIVE LOGITS
    ©¶æ
    0.79
    lectic
    0.72
    mosp
    0.67
    criptions
    0.65
    pite
    0.60
    mos
    0.59
    agnetic
    0.57
    orrow
    0.57
     Pradesh
    0.56
    bians
    0.55
    Act Density 0.132%

    No Known Activations