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

    Neuronpedia

    INDEX
    Explanations

    time-related phrases and durations

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a time frame or duration.

    oai_token-act-pair · gpt-4oTriggered by @459865181

    time-related phrases indicating durations or timelines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oard
    -0.62
    uph
    -0.61
     couch
    -0.61
    inse
    -0.61
     shel
    -0.61
     sofa
    -0.59
     fault
    -0.58
    raught
    -0.58
     bluff
    -0.58
    reon
    -0.58
    POSITIVE LOGITS
     increments
    0.99
     span
    0.91
     intervals
    0.75
     ago
    0.71
    Shape
    0.68
     nutshell
    0.67
    hops
    0.64
     fashion
    0.64
    opian
    0.64
    zers
    0.64
    Act Density 0.111%

    No Known Activations