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

    Neuronpedia

    INDEX
    Explanations

    words related to determination and persistence

    oai_token-act-pair · gpt-3.5-turbo

    nouns and their variations in terms of grammatical structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ridges
    -0.84
    INESS
    -0.75
    TRUMP
    -0.73
    lished
    -0.73
    abase
    -0.72
    Room
    -0.70
    Fill
    -0.68
    BOOK
    -0.68
    govtrack
    -0.68
    Line
    -0.68
    POSITIVE LOGITS
     peanut
    0.69
     grass
    0.67
    pha
    0.64
     mete
    0.64
    onite
    0.63
     soccer
    0.62
    cium
    0.60
     cleric
    0.60
     bloc
    0.60
     Lent
    0.59
    Act Density 0.152%

    No Known Activations