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

    Neuronpedia

    INDEX
    Explanations

    Key technical terms and concepts related to systems and configurations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    apur
    -0.16
    taj
    -0.15
    ÑĢаб
    -0.15
    éra
    -0.14
    ller
    -0.14
    Ñİк
    -0.14
    ofilm
    -0.14
    âĢ¦↵↵↵
    -0.14
    alette
    -0.14
     Cumhur
    -0.13
    POSITIVE LOGITS
     sacrifices
    0.16
    eb
    0.16
    fox
    0.15
     assistant
    0.15
     cane
    0.14
     nutrition
    0.14
    usa
    0.14
     assistants
    0.14
    ARED
    0.14
    ushman
    0.14
    Act Density 0.002%

    No Known Activations