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

    Neuronpedia

    INDEX
    Explanations

    references to individuals, particularly using pronouns and titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cie
    -0.16
    าà¸ĩว
    -0.15
    sWith
    -0.15
    бÑĥдÑĮ
    -0.14
    .fhir
    -0.14
    ãİ¡
    -0.14
    azzi
    -0.13
    ãĤ¤ãĥ³ãĥĪ
    -0.13
    ãĤ¤ãĥ¤
    -0.13
    slick
    -0.13
    POSITIVE LOGITS
    iner
    0.15
    alty
    0.14
    hol
    0.14
     ç¦
    0.13
    bel
    0.13
    BorderColor
    0.13
    onde
    0.13
    æ³½
    0.13
     stddev
    0.13
    445
    0.13
    Act Density 0.021%

    No Known Activations