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

    Neuronpedia

    INDEX
    Explanations

    phrases related to predetermined or fixed parameters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    первых
    -0.67
     tartalomajánló
    -0.59
     achtergrond
    -0.58
     ***!
    -0.58
     /\.
    -0.57
     gyhoeddwyd
    -0.57
    iber
    -0.55
     المعيارى
    -0.55
    новниш
    -0.54
    انجليز
    -0.54
    POSITIVE LOGITS
     fixed
    1.02
     Fixed
    0.85
    Fixed
    0.82
    fixed
    0.81
    FIXED
    0.79
     predefined
    0.76
     predetermined
    0.75
     FIXED
    0.75
    固定
    0.74
    定
    0.71
    Act Density 0.676%

    No Known Activations