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

    Neuronpedia

    INDEX
    Explanations

    the repetition of the word "same."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ses
    -0.17
    ayd
    -0.15
    dal
    -0.14
    ync
    -0.14
    ç½
    -0.14
    uegos
    -0.14
    	templateUrl
    -0.14
     Yates
    -0.14
    ibble
    -0.13
    anter
    -0.13
    POSITIVE LOGITS
    -sex
    0.20
    ÌĨ
    0.20
    steller
    0.16
    _attach
    0.15
    uron
    0.15
    боÑĤ
    0.15
    åŁĭ
    0.14
    åıĸãĤĬ
    0.14
    ouser
    0.14
    unt
    0.14
    Act Density 0.011%

    No Known Activations