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

    Neuronpedia

    INDEX
    Explanations

    words associated with self-reflection and personal growth

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    emer
    -0.16
    æŦ
    -0.16
    िध
    -0.14
    -tags
    -0.14
    levard
    -0.14
    ãĤ«ãĥ«
    -0.14
    674
    -0.14
    erna
    -0.13
    nesia
    -0.13
     нал
    -0.13
    POSITIVE LOGITS
    /un
    0.24
    oppable
    0.20
    nowled
    0.20
    unately
    0.20
    ables
    0.20
    odox
    0.19
    ingly
    0.18
    (Un
    0.17
    untime
    0.17
    izedName
    0.17
    Act Density 0.043%

    No Known Activations