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

    Neuronpedia

    INDEX
    Explanations

    phrases related to performing actions or tasks

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "do it."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Opposition
    -0.72
     opinions
    -0.63
     Returning
    -0.61
     Flavoring
    -0.59
    ²
    -0.57
     Represent
    -0.56
    herent
    -0.56
    holders
    -0.55
    è¦
    -0.54
     Ware
    -0.53
    POSITIVE LOGITS
    alian
    1.03
    self
    0.90
    wrong
    0.90
    chy
    0.89
     justice
    0.86
     anyway
    0.86
    selves
    0.84
     anonymously
    0.84
     anyways
    0.82
     yourself
    0.82
    Act Density 0.065%

    No Known Activations