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

    Neuronpedia

    INDEX
    Explanations

    the word "through" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ised
    -0.16
    zed
    -0.14
    iments
    -0.14
    aken
    -0.14
     μην
    -0.14
    suppress
    -0.14
    andes
    -0.13
    oki
    -0.13
    akens
    -0.13
    æį®
    -0.13
    POSITIVE LOGITS
    ought
    0.35
    puts
    0.34
    -out
    0.31
    OUT
    0.30
    ly
    0.30
    put
    0.28
    out
    0.28
    ogh
    0.28
    ough
    0.27
    /by
    0.27
    Act Density 0.089%

    No Known Activations