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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a request or call for action

    oai_token-act-pair · gpt-3.5-turbo

    phrases that contain the word "for" indicating requests or demands

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    illin
    -0.77
    mare
    -0.72
    oller
    -0.71
    LAB
    -0.67
    fleet
    -0.67
    Ohio
    -0.66
    onen
    -0.64
    Strange
    -0.61
    cles
    -0.61
    plate
    -0.60
    POSITIVE LOGITS
    gotten
    1.16
    geries
    1.14
    gery
    1.12
    bidden
    1.08
     instance
    1.06
     example
    1.04
     centuries
    0.95
     awhile
    0.93
     purposes
    0.91
    ked
    0.91
    Act Density 0.477%

    No Known Activations