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

    Neuronpedia

    INDEX
    Explanations

    comparisons indicating a higher quantity or intensity

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating an increase or a higher quantity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xtap
    -0.92
    IPS
    -0.74
    Age
    -0.70
    liest
    -0.68
    Guard
    -0.66
    atan
    -0.65
    ĺħ
    -0.64
    DragonMagazine
    -0.64
    ffe
    -0.64
    ļé
    -0.63
    POSITIVE LOGITS
     than
    1.43
     Than
    0.96
     stringent
    0.95
     ado
    0.94
     expensive
    0.86
     sophisticated
    0.86
    than
    0.85
     valuable
    0.84
     efficient
    0.82
     realistic
    0.79
    Act Density 0.147%

    No Known Activations