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

    Neuronpedia

    INDEX
    Explanations

    phrases related to specific actions or events happening at a certain moment or being concluded

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "at" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eria
    -0.74
    izo
    -0.71
    reviewed
    -0.65
    adays
    -0.63
    uph
    -0.63
    isters
    -0.61
    iland
    -0.61
    llor
    -0.61
    audi
    -0.59
    ority
    -0.59
    POSITIVE LOGITS
     intervals
    1.04
     whim
    1.00
     least
    0.95
    onement
    0.94
     random
    0.94
     halftime
    0.93
     slightest
    0.91
     inconvenient
    0.90
     anytime
    0.89
     dusk
    0.89
    Act Density 0.118%

    No Known Activations