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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "through" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    through

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nonUne
    -0.40
    intios
    -0.40
     Exacts
    -0.39
    lijkse
    -0.38
    istoitu
    -0.38
     nadie
    -0.37
     guste
    -0.37
    pergillus
    -0.36
    ondres
    -0.35
     ktorá
    -0.35
    POSITIVE LOGITS
     through
    0.57
    through
    0.56
     THROUGH
    0.53
     Through
    0.50
    THROUGH
    0.48
    0.48
     attraverso
    0.45
    Through
    0.45
    ruptedException
    0.45
    Через
    0.43
    Act Density 0.013%

    No Known Activations