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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "begin" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    allo
    -0.71
    atti
    -0.69
    eros
    -0.67
    model
    -0.66
    arial
    -0.65
    aths
    -0.65
    rats
    -0.65
    era
    -0.65
    quickShipAvailable
    -0.65
    olded
    -0.64
    POSITIVE LOGITS
     anew
    1.26
     circulating
    0.84
    ŃĶ
    0.80
     experimenting
    0.80
     transitioning
    0.79
     preparations
    0.78
    nings
    0.78
     hostilities
    0.76
     withdrawing
    0.75
     airing
    0.75
    Act Density 0.045%

    No Known Activations