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

    Neuronpedia

    INDEX
    Explanations

    references to a specific location and its performance metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     January
    -0.17
    ames
    -0.16
    udiant
    -0.16
     Tro
    -0.15
     Jan
    -0.14
    ī
    -0.14
     Flesh
    -0.14
    _One
    -0.14
     imagin
    -0.14
     synd
    -0.14
    POSITIVE LOGITS
    08
    0.30
    05
    0.29
    06
    0.29
    07
    0.28
    09
    0.28
    04
    0.24
    097
    0.18
    078
    0.17
    085
    0.17
    052
    0.17
    Act Density 0.053%

    No Known Activations