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

    Neuronpedia

    INDEX
    Explanations

    affirmative responses or agreements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    munk
    -0.78
    */}
    -0.71
     "));
    -0.71
    multer
    -0.71
    》.
    -0.70
    UIControlState
    -0.69
    ']").
    -0.69
    felves
    -0.68
    ();*/
    -0.66
    ertor
    -0.66
    POSITIVE LOGITS
     YES
    1.49
     Yes
    1.48
    Yes
    1.40
    YES
    1.40
     yes
    1.38
    yes
    1.35
    Yess
    1.01
     Sì
    0.93
     Sí
    0.92
     Noyes
    0.92
    Act Density 0.042%

    No Known Activations