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

    Neuronpedia

    INDEX
    Explanations

    verbs and phrases that indicate action or movement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Kaz
    -0.15
     Ko
    -0.15
     Kaiser
    -0.14
     Kerr
    -0.14
    udur
    -0.13
    ниÑĨе
    -0.13
     Kush
    -0.13
    LÄ°
    -0.13
     kp
    -0.13
     kaz
    -0.13
    POSITIVE LOGITS
    ARK
    0.42
    ark
    0.42
    RK
    0.38
    rk
    0.38
     Bark
    0.37
     McK
    0.37
    NK
    0.37
    irk
    0.36
     RK
    0.36
     BK
    0.36
    Act Density 0.348%

    No Known Activations