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

    Neuronpedia

    INDEX
    Explanations

    time-related expressions highlighting the duration or interval since a particular event occurred

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the passage of time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Cu
    -0.71
    Da
    -0.67
    Si
    -0.66
    Tier
    -0.66
    Fal
    -0.64
    Fight
    -0.64
    Bird
    -0.63
    Mi
    -0.63
    ãĥīãĥ©
    -0.62
    Eye
    -0.62
    POSITIVE LOGITS
    rely
    0.95
    mbuds
    0.76
    ĸļ
    0.72
     completing
    0.69
     inception
    0.68
     contracting
    0.67
     hiatus
    0.66
     rejecting
    0.65
     condemning
    0.65
     arriving
    0.64
    Act Density 0.023%

    No Known Activations