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

    Neuronpedia

    INDEX
    Explanations

    comparisons of quantities

    oai_token-act-pair · gpt-3.5-turbo

    phrases or contexts emphasizing quantities or comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xtap
    -0.80
    ħĭ
    -0.79
    essage
    -0.77
    ĺħ
    -0.74
    ¬¼
    -0.71
    ı
    -0.70
    vised
    -0.69
    atan
    -0.69
    ij士
    -0.66
    »Ĵ
    -0.65
    POSITIVE LOGITS
     than
    1.92
    than
    1.42
     Than
    1.40
     ado
    0.84
     mouths
    0.78
     bang
    0.76
     importantly
    0.72
    Th
    0.70
     mileage
    0.69
     TH
    0.68
    Act Density 0.126%

    No Known Activations