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

    Neuronpedia

    INDEX
    Explanations

    words indicating action or movement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    è¸
    -0.15
    URRED
    -0.15
    urus
    -0.14
    ospace
    -0.14
    ofilm
    -0.14
     nonatomic
    -0.14
     mặc
    -0.14
    ureka
    -0.14
    ivo
    -0.14
    ruc
    -0.14
    POSITIVE LOGITS
     center
    0.28
     aim
    0.28
     centre
    0.27
     on
    0.22
    aim
    0.22
     flight
    0.21
     shape
    0.21
     Aim
    0.20
     Center
    0.20
     readers
    0.20
    Act Density 0.045%

    No Known Activations