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

    Neuronpedia

    INDEX
    Explanations

    quotations within text

    oai_token-act-pair · gpt-3.5-turbo

    quoted speech within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ensen
    -0.76
    âĹ¼
    -0.73
     Archdemon
    -0.71
     Meier
    -0.69
    manship
    -0.68
     Archangel
    -0.64
    ãĥ¼ãĥ«
    -0.63
     Gott
    -0.60
    pps
    -0.60
    ighed
    -0.59
    POSITIVE LOGITS
    Interstitial
    1.23
    MpServer
    1.07
    taboola
    0.98
    avez
    0.83
    yip
    0.79
    erate
    0.78
    ructose
    0.77
    uminium
    0.75
    ieri
    0.74
    Mech
    0.74
    Act Density 0.046%

    No Known Activations