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

    Neuronpedia

    INDEX
    Explanations

    mentions of the name "Se" with a numerical value in the document

    oai_token-act-pair · gpt-3.5-turbo

    references to the character or individual named "Se."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etheless
    -0.84
    £ı
    -0.80
     diplom
    -0.75
    iants
    -0.72
    uracy
    -0.70
     hoops
    -0.68
     CPC
    -0.68
     banter
    -0.66
     scales
    -0.65
     resting
    -0.64
    POSITIVE LOGITS
    eker
    1.33
    vere
    1.24
    ldom
    1.17
    asons
    1.11
    infeld
    1.07
    clusion
    1.05
    gments
    1.05
    eps
    1.05
    gregation
    1.03
    greg
    1.03
    Act Density 0.015%

    No Known Activations