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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating possibility or likelihood regarding future events or scenarios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ickers
    -0.15
    ups
    -0.14
     Ents
    -0.14
    icker
    -0.14
    uggle
    -0.13
    osate
    -0.13
    UnderTest
    -0.13
    -hooks
    -0.13
     Cunningham
    -0.13
    ennen
    -0.13
    POSITIVE LOGITS
    .getAs
    0.17
    anta
    0.16
    ouns
    0.15
    WebKit
    0.14
    CRE
    0.13
    /topics
    0.13
    论åĿĽ
    0.13
     Edge
    0.13
    iedo
    0.13
    441
    0.13
    Act Density 0.106%

    No Known Activations