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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "through" and related phrases indicating processes or sequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    WebServlet
    -0.73
     blessés
    -0.71
     PUBL
    -0.71
     AdapterView
    -0.69
     Púb
    -0.69
     Fabri
    -0.68
     sauvages
    -0.66
    irrit
    -0.65
     Reiz
    -0.65
     Salford
    -0.64
    POSITIVE LOGITS
    Through
    1.91
    THROUGH
    1.86
    through
    1.83
     Through
    1.82
     through
    1.78
     THROUGH
    1.68
     thru
    1.48
     Thru
    1.37
     través
    1.36
    thru
    1.33
    Act Density 0.146%

    No Known Activations