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

    Neuronpedia

    INDEX
    Explanations

    verbs related to taking a certain action or making a particular statement

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     lü
    -0.62
     Oma
    -0.60
     panik
    -0.59
     alkoh
    -0.58
     kosme
    -0.55
     Letra
    -0.54
     induk
    -0.54
     elektronik
    -0.53
     rü
    -0.53
     kemer
    -0.53
    POSITIVE LOGITS
     pose
    1.37
     poses
    1.33
     posed
    1.29
     posing
    1.28
     Pose
    1.07
    pose
    1.04
     poser
    0.97
    Pose
    0.95
    poses
    0.93
     posé
    0.92
    Act Density 0.067%

    No Known Activations