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

    Neuronpedia

    INDEX
    Explanations

    phrases related to reaching a critical point or threshold

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating critical situations or thresholds

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    è¦ļéĨĴ
    -0.64
    CVE
    -0.64
    anism
    -0.61
     Kinnikuman
    -0.60
    enne
    -0.59
    atto
    -0.58
    via
    -0.57
     laund
    -0.57
     segregated
    -0.57
    tein
    -0.55
    POSITIVE LOGITS
    manship
    1.43
     brink
    1.14
    terness
    0.97
     verge
    0.86
    faced
    0.78
    cape
    0.77
    pex
    0.74
    dash
    0.73
    layer
    0.71
    ï¸
    0.71
    Act Density 0.017%

    No Known Activations