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

    Neuronpedia

    INDEX
    Explanations

    statements and phrases that indicate uncertainty or speculation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    มà¸ķ
    -0.16
    iasi
    -0.15
    inson
    -0.15
    nio
    -0.15
    buat
    -0.15
    .hw
    -0.15
    isci
    -0.14
    æ¬ł
    -0.14
    alta
    -0.14
    elerik
    -0.14
    POSITIVE LOGITS
    enger
    0.18
     Inputs
    0.15
    ymph
    0.15
    arge
    0.15
    ellen
    0.14
     Pra
    0.14
     Pillow
    0.14
    λαν
    0.14
    oller
    0.14
    ab
    0.14
    Act Density 0.267%

    No Known Activations