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

    Neuronpedia

    INDEX
    Explanations

    expressions of time duration

    oai_token-act-pair · gpt-3.5-turbo

    quantities or durations of time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ħĭ
    -0.83
    vec
    -0.76
    ailability
    -0.74
    urden
    -0.74
     Lastly
    -0.72
    Edge
    -0.72
    âĶģ
    -0.71
    Ü
    -0.70
    anity
    -0.70
    ntil
    -0.70
    POSITIVE LOGITS
     weeks
    1.17
     months
    1.14
     tries
    1.11
     days
    1.11
     years
    1.10
     seconds
    1.06
     hours
    1.05
     minutes
    1.05
     YEAR
    1.01
     hrs
    1.01
    Act Density 0.076%

    No Known Activations