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

    Neuronpedia

    INDEX
    Explanations

    global entities and concepts

    oai_token-act-pair · gpt-3.5-turbo

    references to lists and categories of items or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ¦ãĤ¹
    -0.99
    Í
    -0.71
    \\\\\\\\
    -0.69
    tainment
    -0.69
    cffffcc
    -0.69
    ķ
    -0.66
    ãĤ´ãĥ³
    -0.65
     Opportun
    -0.64
    powers
    -0.63
    amation
    -0.63
    POSITIVE LOGITS
     listed
    1.37
     surveyed
    1.31
     mentioned
    1.23
     involved
    1.21
     cited
    1.20
     discussed
    1.20
     examined
    1.19
     reviewed
    1.13
     interviewed
    1.12
     studied
    1.11
    Act Density 0.373%

    No Known Activations