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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "see" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ly
    -0.20
    sten
    -0.18
    pcs
    -0.16
    cai
    -0.15
    phere
    -0.15
    media
    -0.15
    pir
    -0.15
     suy
    -0.15
    erial
    -0.15
    ster
    -0.15
    POSITIVE LOGITS
    /he
    0.24
    -through
    0.19
     cref
    0.17
     xét
    0.17
    -eye
    0.15
    uw
    0.15
    kili
    0.15
    eking
    0.15
    pras
    0.15
    dust
    0.15
    Act Density 0.124%

    No Known Activations