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

    Neuronpedia

    INDEX
    Explanations

    time-related terms and durations

    oai_token-act-pair · gpt-3.5-turbo

    time-related expressions and durations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tnc
    -0.75
     indemn
    -0.70
    bard
    -0.70
    irie
    -0.70
    fml
    -0.69
     kindred
    -0.68
    SpaceEngineers
    -0.68
     counterfe
    -0.68
    guard
    -0.66
    Australian
    -0.63
    POSITIVE LOGITS
     elapsed
    1.03
     allotted
    0.84
     seconds
    0.82
    apsed
    0.79
    Cooldown
    0.79
     duration
    0.76
     minutes
    0.74
     devoted
    0.73
     runtime
    0.73
     narration
    0.72
    Act Density 0.271%

    No Known Activations