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

    Neuronpedia

    INDEX
    Explanations

    the word 'Es' followed by a numerical value from 3 to 10

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Es" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DragonMagazine
    -0.78
     guiActiveUnfocused
    -0.69
     IMAGES
    -0.66
     underside
    -0.64
    erous
    -0.61
    ãģĮ
    -0.61
     sund
    -0.61
    mallow
    -0.60
     cooker
    -0.60
    arity
    -0.59
    POSITIVE LOGITS
    quire
    1.15
    oteric
    1.13
    ternal
    0.97
    plin
    0.96
    urance
    0.95
    earchers
    0.94
    una
    0.94
    ync
    0.94
    cham
    0.92
    ury
    0.90
    Act Density 0.016%

    No Known Activations