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

    Neuronpedia

    INDEX
    Explanations

    references to significant events and feelings of opportunity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oling
    -0.17
     når
    -0.15
    ertas
    -0.14
    ži
    -0.14
    anko
    -0.14
     nhá»Ŀ
    -0.14
    eson
    -0.14
    åĩĮ
    -0.13
    prevent
    -0.13
     Wyn
    -0.13
    POSITIVE LOGITS
     knowing
    0.27
     hoping
    0.25
    hop
    0.24
    expect
    0.23
     leaving
    0.21
     expecting
    0.20
     Knowing
    0.19
     Hop
    0.17
     feeling
    0.17
    know
    0.17
    Act Density 0.061%

    No Known Activations