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

    Neuronpedia

    INDEX
    Explanations

    the presence of the term "em" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vet
    -0.17
    ÙĨب
    -0.16
    p
    -0.16
    ings
    -0.15
    pard
    -0.15
    ãĥ©ãĤ¤ãĥĪ
    -0.14
    averse
    -0.14
    odox
    -0.14
    agnostic
    -0.14
    xia
    -0.14
    POSITIVE LOGITS
     em
    0.29
    erald
    0.25
     Em
    0.22
    manuel
    0.21
    (em
    0.20
    brace
    0.20
    .em
    0.20
    cee
    0.19
    itters
    0.19
    ulating
    0.19
    Act Density 0.017%

    No Known Activations