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

    Neuronpedia

    INDEX
    Explanations

    years mentioned in historical contexts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "In" followed by a numerical reference or date

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     lett
    -0.70
     spoil
    -0.70
     behav
    -0.69
     ingred
    -0.67
     looms
    -0.63
     lodged
    -0.63
     combatants
    -0.63
     selves
    -0.62
     babe
    -0.62
     outwe
    -0.61
    POSITIVE LOGITS
    ventory
    1.38
    cluding
    1.37
    clusion
    1.25
    juries
    1.23
     addition
    1.21
    jection
    1.20
    jured
    1.18
    jury
    1.16
    cluded
    1.15
     lieu
    1.15
    Act Density 0.147%

    No Known Activations