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

    Neuronpedia

    INDEX
    Explanations

    phrases related to programming and technical topics

    oai_token-act-pair · gpt-3.5-turbo

    instances of the abbreviation "Pl" followed by a number

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    âĸ¬âĸ¬
    -0.88
    âĸ¬
    -0.78
    ãģ®éŃĶ
    -0.76
    gerald
    -0.73
    ~~~~
    -0.71
    eers
    -0.69
    worthiness
    -0.68
    ãĥĨãĤ£
    -0.66
    eer
    -0.66
     FANTASY
    -0.65
    POSITIVE LOGITS
    utonium
    1.24
    acement
    1.21
    atoon
    1.19
    atinum
    1.14
    atter
    1.14
    asma
    1.12
    ausible
    1.10
    umber
    1.07
    enty
    1.07
    umbing
    1.06
    Act Density 0.022%

    No Known Activations