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

    Neuronpedia

    INDEX
    Explanations

    phrases related to guide books or instructional resources

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "guide" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Rated
    -0.79
    ammy
    -0.65
    asted
    -0.65
    POSE
    -0.65
    enos
    -0.64
     spect
    -0.63
    ntil
    -0.61
     forfeit
    -0.61
    nesota
    -0.60
     concess
    -0.59
    POSITIVE LOGITS
    book
    1.48
    books
    1.34
    posts
    1.13
    BOOK
    0.96
    guide
    0.91
    Book
    0.88
    kit
    0.86
     guide
    0.85
     guides
    0.84
     Guide
    0.79
    Act Density 0.075%

    No Known Activations