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

    Neuronpedia

    INDEX
    Explanations

    dates and times

    oai_token-act-pair · gpt-3.5-turbo

    dates and numerical identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ayan
    -0.86
    anka
    -0.76
    aya
    -0.73
     Rah
    -0.68
    ount
    -0.68
     Flores
    -0.68
    index
    -0.67
     Airways
    -0.64
    hw
    -0.63
     HUN
    -0.63
    POSITIVE LOGITS
    3
    1.53
     3
    1.48
     Three
    1.18
    three
    1.13
    Three
    1.07
     III
    1.05
     three
    1.03
     THREE
    0.98
     Third
    0.96
     trio
    0.93
    Act Density 0.190%

    No Known Activations