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

    Neuronpedia

    INDEX
    Explanations

    indicators of research findings and evidence in studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    çŁ¢
    -0.14
    BoundingBox
    -0.13
    rix
    -0.13
    ÏħÏĦÏĮ
    -0.13
    hib
    -0.13
    etrofit
    -0.13
    ιδ
    -0.13
    dep
    -0.13
    audi
    -0.13
    clip
    -0.12
    POSITIVE LOGITS
     clear
    0.26
     there
    0.25
     links
    0.24
     marked
    0.22
     promise
    0.22
     strong
    0.22
     conclus
    0.22
     how
    0.21
    links
    0.20
    marked
    0.20
    Act Density 0.084%

    No Known Activations