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

    Neuronpedia

    INDEX
    Explanations

    references to software versioning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Charging
    -0.15
    ulin
    -0.15
    ÑĢаж
    -0.14
    ues
    -0.14
    /Dk
    -0.14
    shot
    -0.14
    ote
    -0.14
     avis
    -0.14
    prit
    -0.14
     unavoid
    -0.14
    POSITIVE LOGITS
    /version
    0.15
    naires
    0.15
     addCriterion
    0.15
     Meadows
    0.15
    anax
    0.14
    aires
    0.14
     $#
    0.14
    تا
    0.14
    awah
    0.14
    aleigh
    0.14
    Act Density 0.024%

    No Known Activations