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

    Neuronpedia

    INDEX
    Explanations

    sections labeled "About" or similar introductory phrases regarding topics or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aid
    -0.15
    ught
    -0.15
    agem
    -0.15
    gun
    -0.15
    ammers
    -0.14
     treff
    -0.14
    ield
    -0.14
    enting
    -0.14
     architectural
    -0.14
    sg
    -0.14
    POSITIVE LOGITS
    Derived
    0.14
    itzer
    0.14
    ÏĨη
    0.14
    ůr
    0.14
    á»ķ
    0.14
    izzie
    0.14
    rawn
    0.13
    #!
    0.13
    azi
    0.13
    ledged
    0.13
    Act Density 0.015%

    No Known Activations