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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a duration of time or a waiting period

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating duration and ongoing actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Secondly
    -0.73
     secondly
    -0.72
    lihood
    -0.70
     Shutterstock
    -0.68
    later
    -0.67
     tomorrow
    -0.67
     [+
    -0.65
    iscons
    -0.64
    */(
    -0.63
     similarity
    -0.63
    POSITIVE LOGITS
     maintained
    0.91
     waged
    0.91
     resided
    0.88
     tirelessly
    0.88
     uninterrupted
    0.88
     dogged
    0.87
     relentlessly
    0.87
     altern
    0.86
     steadfast
    0.85
     steadily
    0.85
    Act Density 0.354%

    No Known Activations