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

    Neuronpedia

    INDEX
    Explanations

    mentions of reviews or ratings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vince
    -0.16
    ghi
    -0.16
    gow
    -0.15
    fol
    -0.15
    308
    -0.15
     Barbar
    -0.15
    uraa
    -0.15
    uida
    -0.14
    adena
    -0.14
    ylvania
    -0.14
    POSITIVE LOGITS
    raÄį
    0.16
    ħ
    0.16
    ing
    0.16
    ĤŃ
    0.16
    rain
    0.16
    ables
    0.15
    nder
    0.15
    ÑĢеменно
    0.15
    ably
    0.15
    /meta
    0.15
    Act Density 0.049%

    No Known Activations