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

    Neuronpedia

    INDEX
    Explanations

    phrases related to beginnings and starting actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     отношению
    -0.73
     ​​
    -0.72
    MathML
    -0.70
    /***/
    -0.70
    StructEnd
    -0.69
    خدام
    -0.69
    avedra
    -0.69
    gdx
    -0.67
    UTERS
    -0.66
     Walton
    -0.65
    POSITIVE LOGITS
     Begin
    1.01
    begins
    0.98
     begun
    0.98
     begin
    0.93
    began
    0.92
     Begins
    0.90
     BEGINNING
    0.89
     BEGIN
    0.89
     began
    0.85
     Bergman
    0.84
    Act Density 0.105%

    No Known Activations