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

    Neuronpedia

    INDEX
    Explanations

    references to chat functionality and chat boxes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Datuak
    -0.80
     Briggs
    -0.69
    projectile
    -0.62
    ]}"
    -0.61
    BoxShadow
    -0.61
    ≡
    -0.60
    annulation
    -0.60
    AMT
    -0.60
     Kej
    -0.59
    Escola
    -0.59
    POSITIVE LOGITS
     pose
    1.16
     Relax
    1.08
     poses
    1.07
     Pose
    1.07
    relax
    1.06
     relaxes
    1.06
     relax
    1.03
     posing
    1.03
     rilass
    1.01
    Relax
    1.00
    Act Density 0.064%

    No Known Activations