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

    Neuronpedia

    INDEX
    Explanations

    references to personally identifiable information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oked
    -0.15
    ér
    -0.14
    irt
    -0.14
    isen
    -0.13
    _compress
    -0.13
    ÃŃž
    -0.13
    &r
    -0.13
     prefer
    -0.13
    heimer
    -0.13
     Trev
    -0.13
    POSITIVE LOGITS
    993
    0.16
     gord
    0.16
     Guerrero
    0.15
    931
    0.14
    ango
    0.14
    343
    0.14
     Ib
    0.14
    axon
    0.14
    ypress
    0.14
    ypi
    0.14
    Act Density 0.003%

    No Known Activations