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

    Neuronpedia

    INDEX
    Explanations

    financial figures and dates in various formats

    oai_token-act-pair · gpt-3.5-turbo

    monetary values and dates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     KH
    -0.99
     Ott
    -0.98
     Tak
    -0.91
     Kahn
    -0.88
     Kan
    -0.85
     Izan
    -0.84
     Panc
    -0.82
     Mahjong
    -0.80
     ak
    -0.80
     Ops
    -0.79
    POSITIVE LOGITS
    30
    1.37
    29
    1.35
    28
    1.31
     29
    1.25
     30
    1.24
    31
    1.24
     28
    1.22
     31
    1.12
    27
    1.07
    298
    1.07
    Act Density 0.284%

    No Known Activations