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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "se."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    a
    -0.15
    ubar
    -0.15
    an
    -0.15
    инÑĥв
    -0.14
     Herm
    -0.14
    usement
    -0.14
    539
    -0.14
    ek
    -0.14
    928
    -0.14
    ter
    -0.14
    POSITIVE LOGITS
    aside
    0.23
    amus
    0.21
    vere
    0.21
    ismic
    0.20
    ating
    0.20
    ated
    0.20
    aled
    0.19
    clusion
    0.19
    bring
    0.19
    als
    0.19
    Act Density 0.011%

    No Known Activations