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

    Neuronpedia

    INDEX
    Explanations

    phrases related to processes or activities that are in progress

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "the."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bots
    -0.75
    ago
    -0.72
    adoes
    -0.68
     derives
    -0.67
    href
    -0.66
     accordingly
    -0.65
    ographers
    -0.65
    omen
    -0.64
    bugs
    -0.64
     arises
    -0.64
    POSITIVE LOGITS
     forefront
    1.26
     midst
    1.08
     safest
    0.94
     same
    0.93
     verge
    0.91
     foreground
    0.90
     happiest
    0.89
     wrong
    0.87
     thro
    0.85
     deepest
    0.84
    Act Density 0.209%

    No Known Activations