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

    Neuronpedia

    INDEX
    Explanations

    quotes and dialogues within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     BELOW
    -0.14
     Warning
    -0.14
    WARNING
    -0.14
    Known
    -0.14
     лиÑĪÑĮ
    -0.14
     WARNING
    -0.14
    NOTE
    -0.14
    nerg
    -0.14
     NOTE
    -0.13
    æѤ
    -0.13
    POSITIVE LOGITS
     somebody
    0.24
     definitely
    0.23
     certainly
    0.23
     We
    0.23
     really
    0.22
     [
    0.21
     everybody
    0.21
     I
    0.19
     particularly
    0.19
     Somebody
    0.19
    Act Density 0.103%

    No Known Activations