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

    Neuronpedia

    INDEX
    Explanations

    contractions of "do not"

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "don't" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     exha
    -0.64
     circ
    -0.63
    EStreamFrame
    -0.60
     pus
    -0.59
    milo
    -0.59
     liberated
    -0.59
     Worlds
    -0.58
     Rated
    -0.58
     fulfilled
    -0.57
     Ability
    -0.57
    POSITIVE LOGITS
    't
    1.67
    ovan
    1.08
    ning
    1.01
    uts
    0.99
    ned
    0.96
    ÃŃ
    0.94
    keys
    0.94
    itely
    0.91
    ating
    0.91
    nel
    0.89
    Act Density 0.034%

    No Known Activations