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

    Neuronpedia

    INDEX
    Explanations

    references to opinions and viewpoints

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orian
    -0.18
    chner
    -0.18
    lsi
    -0.17
    gow
    -0.16
    uras
    -0.15
    ampion
    -0.15
    OOM
    -0.15
    tica
    -0.15
    lear
    -0.15
    ey
    -0.15
    POSITIVE LOGITS
    aires
    0.21
    naire
    0.19
    ated
    0.19
    ally
    0.18
    /op
    0.18
    ably
    0.17
    naires
    0.16
    ster
    0.16
    /tutorial
    0.16
    ATED
    0.15
    Act Density 0.022%

    No Known Activations