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

    Neuronpedia

    INDEX
    Explanations

    text indicating an example or illustration

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "For" used to introduce examples or explanations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    soType
    -0.76
    buster
    -0.71
    ãĤ´ãĥ³
    -0.68
    ickle
    -0.63
    ãĥIJ
    -0.63
    eat
    -0.61
    sonian
    -0.61
     coincides
    -0.61
    smanship
    -0.60
    ru
    -0.60
    POSITIVE LOGITS
     example
    1.92
     instance
    1.65
     Example
    1.26
     simplicity
    1.25
    cing
    1.22
    gotten
    1.19
     starters
    1.18
    bidden
    1.13
    example
    1.11
    give
    1.09
    Act Density 0.088%

    No Known Activations