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

    Neuronpedia

    INDEX
    Explanations

    instances of punctuation, particularly periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ">//
    -0.17
    ìľĦ
    -0.15
    ³ç´°
    -0.15
    ozÃŃ
    -0.15
    UPPORTED
    -0.15
    /Dk
    -0.14
    .opensource
    -0.14
    istrovstvÃŃ
    -0.14
    MBED
    -0.14
    eurs
    -0.14
    POSITIVE LOGITS
     ought
    0.19
     now
    0.19
     nothing
    0.17
     should
    0.17
     odds
    0.17
     do
    0.17
    -now
    0.17
    ↵
    0.17
    now
    0.17
     Odds
    0.17
    Act Density 0.005%

    No Known Activations