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

    Neuronpedia

    INDEX
    Explanations

    various forms of the verb "go"

    oai_token-act-pair · gpt-3.5-turbo

    verbs indicating movement or action, particularly in the past and present tenses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Lauder
    -0.71
    theless
    -0.66
    iland
    -0.66
    lain
    -0.63
    heid
    -0.61
    aspers
    -0.61
     Lear
    -0.60
     Qué
    -0.58
    idate
    -0.56
     continuation
    -0.55
    POSITIVE LOGITS
    lems
    0.93
     wrong
    0.90
     aw
    0.86
     unnoticed
    0.82
     Wrong
    0.75
    wrong
    0.75
     viral
    0.74
     ast
    0.73
     missing
    0.73
    lem
    0.71
    Act Density 0.039%

    No Known Activations