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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate contrasting ideas or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    adero
    -0.14
    ango
    -0.14
    237
    -0.14
    emmel
    -0.14
    ÙİÙĥ
    -0.13
    ei
    -0.13
    opp
    -0.13
    Reserved
    -0.13
    aucoup
    -0.13
    ahas
    -0.13
    POSITIVE LOGITS
    Nor
    0.16
     nor
    0.16
     Nor
    0.15
     Prem
    0.14
     rig
    0.14
    onda
    0.14
    foy
    0.14
    etheless
    0.14
     briefing
    0.14
     subs
    0.14
    Act Density 0.175%

    No Known Activations