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

    Neuronpedia

    INDEX
    Explanations

    the word "Boot"

    oai_token-act-pair · gpt-3.5-turbo

    repeated occurrences of the word "foot."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     lapse
    -0.73
     exha
    -0.70
    MIT
    -0.64
     ancest
    -0.63
     agon
    -0.62
     misunder
    -0.62
    riber
    -0.61
    agara
    -0.61
    ĻĤ
    -0.60
     galvan
    -0.59
    POSITIVE LOGITS
    strap
    1.14
    hing
    1.14
    hed
    1.09
    oot
    1.04
    sie
    1.03
    ishly
    0.99
    iful
    0.95
    eers
    0.94
    stra
    0.93
    erness
    0.91
    Act Density 0.023%

    No Known Activations