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

    Neuronpedia

    INDEX
    Explanations

    words related to famous people and brand names

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns or specific names related to individuals or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĸļ
    -0.63
    Thumbnail
    -0.61
     Attribution
    -0.59
    erial
    -0.58
    ernel
    -0.58
    pherd
    -0.57
    mble
    -0.54
    alogue
    -0.54
    ItemImage
    -0.54
     juggling
    -0.54
    POSITIVE LOGITS
    ans
    0.62
    isively
    0.60
    pes
    0.59
    onto
    0.57
    Ts
    0.57
    Care
    0.57
    Ms
    0.55
    Ct
    0.54
    ratom
    0.54
    cit
    0.52
    Act Density 0.537%

    No Known Activations