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

    Neuronpedia

    INDEX
    Explanations

    phrases related to specific time periods

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "During."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     reflex
    -0.67
     ed
    -0.63
     Hook
    -0.63
     arch
    -0.62
     lists
    -0.61
     gloss
    -0.61
     gaping
    -0.60
     others
    -0.60
     fanc
    -0.60
     likes
    -0.60
    POSITIVE LOGITS
    During
    2.96
    Throughout
    1.88
    during
    1.84
    After
    1.81
    Following
    1.75
    Shortly
    1.74
     During
    1.73
    Upon
    1.68
    When
    1.67
    Between
    1.66
    Act Density 0.032%

    No Known Activations