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

    Neuronpedia

    INDEX
    Explanations

    highly cited or acknowledged numerical statistics in a context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    302
    -0.18
    088
    -0.17
     Schmidt
    -0.17
    806
    -0.17
    904
    -0.15
    298
    -0.15
    602
    -0.15
    804
    -0.15
    024
    -0.15
    704
    -0.15
    POSITIVE LOGITS
    100
    0.28
    200
    0.27
    900
    0.23
    400
    0.21
    130
    0.21
    700
    0.21
    70
    0.21
    300
    0.20
    140
    0.19
    90
    0.19
    Act Density 0.061%

    No Known Activations