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

    Neuronpedia

    INDEX
    Explanations

    references to significant events or milestones

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    åª
    -0.18
    GORITH
    -0.15
     Poh
    -0.15
     McMahon
    -0.14
    chy
    -0.14
    ÃŁ
    -0.13
    979
    -0.13
    Ellipse
    -0.13
    ι
    -0.13
     Diss
    -0.13
    POSITIVE LOGITS
     Heads
    0.15
    enberg
    0.15
     Salv
    0.15
    μÏĨ
    0.14
    ubble
    0.14
    PUTE
    0.14
     lng
    0.14
    uth
    0.14
    wagon
    0.14
    oad
    0.13
    Act Density 0.029%

    No Known Activations