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

    Neuronpedia

    INDEX
    Explanations

    phrases that start with "In"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "In" followed by various contexts or descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     unemploy
    -0.76
    $$
    -0.66
     nurt
    -0.65
     artif
    -0.62
     trave
    -0.62
    reon
    -0.61
     combatants
    -0.61
    ilogy
    -0.61
     RIGHT
    -0.60
    resh
    -0.60
    POSITIVE LOGITS
     addition
    1.35
    mates
    1.28
    jured
    1.23
     contrast
    1.23
    spect
    1.20
    cluding
    1.16
     spite
    1.14
    juries
    1.10
    ventory
    1.10
     lieu
    1.05
    Act Density 0.137%

    No Known Activations