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

    Neuronpedia

    INDEX
    Explanations

    instances of administrative actions or announcements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    unday
    -0.18
    acios
    -0.16
    ibold
    -0.15
    icz
    -0.14
    abyrin
    -0.14
    allet
    -0.14
    ffer
    -0.14
    Globals
    -0.14
    orda
    -0.14
    .bridge
    -0.14
    POSITIVE LOGITS
    gang
    0.15
    ÏĨÏħ
    0.15
    rors
    0.14
    ytt
    0.14
     issued
    0.14
    emade
    0.14
    endor
    0.14
    ges
    0.14
    elu
    0.13
    νÏī
    0.13
    Act Density 0.005%

    No Known Activations