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

    Neuronpedia

    INDEX
    Explanations

    instances of violations of laws or principles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iaux
    -0.17
    iae
    -0.17
    oria
    -0.17
    sim
    -0.14
    ì¹Ń
    -0.14
    mie
    -0.14
    /he
    -0.14
     folds
    -0.14
    ons
    -0.13
    ÑĢÑıдÑĥ
    -0.13
    POSITIVE LOGITS
    isini
    0.16
    umont
    0.15
    .Popup
    0.15
    /problem
    0.15
    upert
    0.15
     Mey
    0.15
    iveness
    0.14
    wers
    0.14
    IVE
    0.14
    acz
    0.14
    Act Density 0.025%

    No Known Activations