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

    Neuronpedia

    INDEX
    Explanations

    phrases that discuss changes in perspective or approach

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alc
    -0.17
     Dien
    -0.16
    iani
    -0.16
    folio
    -0.16
    agli
    -0.15
    cede
    -0.15
     èĪ
    -0.14
    lish
    -0.14
    asp
    -0.14
     Rey
    -0.14
    POSITIVE LOGITS
    ushima
    0.16
    ayacak
    0.15
    obot
    0.15
     обл
    0.15
    ervlet
    0.15
    caa
    0.15
    449
    0.15
     Rider
    0.15
     suppress
    0.14
    Straight
    0.14
    Act Density 0.732%

    No Known Activations