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

    Neuronpedia

    INDEX
    Explanations

    phrases that convey a sense of uncertainty or hypothetical situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÏĦÏį
    -0.17
    ugin
    -0.15
     seems
    -0.15
    azzi
    -0.15
    engo
    -0.14
    è²Į
    -0.14
     seemed
    -0.14
     seem
    -0.14
    ãĤīãģĦ
    -0.14
    ÑĮко
    -0.14
    POSITIVE LOGITS
    arel
    0.16
     somehow
    0.15
     Atlas
    0.15
    alara
    0.15
    inous
    0.14
     audition
    0.14
    genden
    0.14
    usher
    0.14
    aign
    0.14
     barely
    0.13
    Act Density 0.095%

    No Known Activations