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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "em" in various forms, suggesting a focus on emotional or expressive content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ©ãĤ¤ãĥĪ
    -0.16
    xia
    -0.15
    vet
    -0.15
    adelphia
    -0.14
    ÙĨب
    -0.14
    p
    -0.14
    amento
    -0.14
    ç©
    -0.14
    odox
    -0.14
    vik
    -0.13
    POSITIVE LOGITS
     em
    0.25
    erald
    0.22
     Em
    0.22
    manuel
    0.20
    (em
    0.20
    .em
    0.20
    erson
    0.18
    sworth
    0.18
    Em
    0.17
    brace
    0.17
    Act Density 0.013%

    No Known Activations