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

    Neuronpedia

    INDEX
    Explanations

    references to changes and their potential impacts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    onders
    -0.15
    ä¸įä¼ļ
    -0.15
    orsch
    -0.15
     Spoon
    -0.14
    iyel
    -0.14
    chaft
    -0.14
    chester
    -0.14
     certainly
    -0.13
    çĦ¡ãģĹãģ
    -0.13
    _Lean
    -0.13
    POSITIVE LOGITS
     affects
    0.25
     affected
    0.24
     relates
    0.24
     affect
    0.23
     fares
    0.23
     differs
    0.22
     differ
    0.22
     relate
    0.21
     differently
    0.21
     afect
    0.20
    Act Density 0.094%

    No Known Activations