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

    Neuronpedia

    INDEX
    Explanations

    phrases related to time durations

    oai_token-act-pair · gpt-3.5-turbo

    phrases or contexts related to prolonged durations or lengthy periods of time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    onom
    -0.82
     Learns
    -0.77
    lik
    -0.71
    ku
    -0.70
    aders
    -0.69
    asive
    -0.69
    urai
    -0.69
    TOP
    -0.68
    alus
    -0.68
    ading
    -0.66
    POSITIVE LOGITS
    rontal
    0.86
     lasting
    0.83
     ordeal
    0.82
     ago
    0.81
     continu
    0.79
     deliberations
    0.78
     hiatus
    0.75
    kered
    0.74
     operation
    0.73
    suff
    0.73
    Act Density 0.020%

    No Known Activations