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

    Neuronpedia

    INDEX
    Explanations

    regulatory or procedural details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Canter
    -0.15
     Hlav
    -0.15
    lor
    -0.14
     Lore
    -0.14
    ãģ«ãģ¦
    -0.14
    OND
    -0.14
    MG
    -0.14
    affer
    -0.13
    Defense
    -0.13
    ÑģÑĤи
    -0.13
    POSITIVE LOGITS
    Directions
    0.18
     subsection
    0.18
    mentioned
    0.17
     directions
    0.17
     mentions
    0.16
     Mention
    0.16
     Directions
    0.16
     mention
    0.15
    ân
    0.15
     mentioned
    0.15
    Act Density 0.014%

    No Known Activations