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

    Neuronpedia

    INDEX
    Explanations

    references to testing frameworks and setup methods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Pron
    -0.15
    dash
    -0.14
    dÃŃ
    -0.14
    avic
    -0.14
    شار
    -0.14
    Exposed
    -0.14
    asher
    -0.14
    imli
    -0.13
    ÑģÑĮк
    -0.13
    wis
    -0.13
    POSITIVE LOGITS
    INGLE
    0.17
    ÛĮدÙĩ
    0.14
     sud
    0.14
    hle
    0.14
    264
    0.14
     Everett
    0.13
    ingly
    0.13
    /Form
    0.13
    apped
    0.13
    .UnitTesting
    0.13
    Act Density 0.015%

    No Known Activations