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

    Neuronpedia

    INDEX
    Explanations

    imperatives and commands related to requests and decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    MLLoader
    -0.59
    罷
    -0.53
    ruptedException
    -0.52
    ximately
    -0.52
    niſſe
    -0.51
    makeConstraints
    -0.49
    LLocation
    -0.49
    IonicModule
    -0.49
    IActionResult
    -0.49
    ưỡi
    -0.48
    POSITIVE LOGITS
    always
    1.00
     Always
    0.98
    Always
    0.98
     always
    0.97
     ALWAYS
    0.94
     siempre
    0.85
    ALWAYS
    0.83
     sempre
    0.82
    siempre
    0.82
     Siempre
    0.81
    Act Density 0.046%

    No Known Activations