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

    Neuronpedia

    INDEX
    Explanations

    time-related expressions, particularly durations like hours and minutes

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to time durations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oid
    -0.72
    oids
    -0.69
    issue
    -0.69
    spons
    -0.68
    enum
    -0.66
    issues
    -0.65
     Franch
    -0.65
    bard
    -0.64
     Matrix
    -0.64
    rets
    -0.63
    POSITIVE LOGITS
     apiece
    1.19
    ftime
    0.80
     ago
    0.76
     intervals
    0.75
     stroll
    0.74
    hops
    0.72
     jog
    0.71
     each
    0.71
     Ago
    0.70
    long
    0.70
    Act Density 0.098%

    No Known Activations