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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "see" and its variations used to introduce statements or observations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etsk
    -0.16
    ons
    -0.16
    ipi
    -0.15
    bra
    -0.15
    ona
    -0.14
    gram
    -0.14
    ãĥ³
    -0.14
    ambi
    -0.14
     Aws
    -0.14
    yll
    -0.14
    POSITIVE LOGITS
    è¼
    0.17
    رÙĪت
    0.15
    è¾
    0.15
    ulong
    0.14
     miá»ĩng
    0.14
    ampp
    0.14
    otas
    0.14
    averse
    0.14
    868
    0.13
    ettle
    0.13
    Act Density 0.021%

    No Known Activations