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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "ever"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ัà¸ģà¸Ķ
    -0.16
    kuk
    -0.15
    sch
    -0.15
    à¤Łà¤°
    -0.15
    arius
    -0.14
    IQ
    -0.14
    gua
    -0.14
    ertype
    -0.14
    scratch
    -0.14
     richt
    -0.14
    POSITIVE LOGITS
    greens
    0.20
    last
    0.19
    lasting
    0.19
    LAST
    0.19
     wonder
    0.18
    theless
    0.18
    green
    0.17
    thing
    0.17
     wondered
    0.17
    yst
    0.17
    Act Density 0.018%

    No Known Activations