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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "the" followed by other specific words

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating repeated events or moments in time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    renheit
    -0.80
    onto
    -0.70
    lections
    -0.68
    ruciating
    -0.64
    rys
    -0.63
     expend
    -0.62
    undo
    -0.62
    ecided
    -0.61
    marine
    -0.60
    ullah
    -0.60
    POSITIVE LOGITS
     outset
    0.79
     moment
    0.75
     conclusion
    0.72
     behest
    0.72
    Exit
    0.71
     end
    0.71
     peak
    0.70
     entrance
    0.68
     scene
    0.65
     completion
    0.65
    Act Density 0.099%

    No Known Activations