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

    Neuronpedia

    INDEX
    Explanations

    proper names, specifically focusing on names of places and people

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific names or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lda
    -0.84
    ============
    -0.80
    HER
    -0.78
    OF
    -0.75
    glers
    -0.75
    ========
    -0.75
    HL
    -0.73
    BLIC
    -0.72
    ãĤ´ãĥ³
    -0.71
    selage
    -0.71
    POSITIVE LOGITS
    shire
    0.94
    axter
    0.82
    ellen
    0.80
     Kut
    0.78
    enton
    0.77
    icum
    0.77
    skill
    0.76
    s
    0.76
    roach
    0.76
    owed
    0.74
    Act Density 0.027%

    No Known Activations