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

    Neuronpedia

    INDEX
    Explanations

    elements related to user input fields and their attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ola
    -0.15
    ät
    -0.15
    741
    -0.15
    atori
    -0.15
    745
    -0.14
    amp
    -0.14
    yo
    -0.14
    shaw
    -0.14
     pur
    -0.13
    serter
    -0.13
    POSITIVE LOGITS
    OffsetTable
    0.16
    veis
    0.15
    anka
    0.15
    æ³ī
    0.15
    INARY
    0.15
    ilters
    0.15
    ãĥŃãĥ¼
    0.15
     استر
    0.15
     示
    0.15
    .gov
    0.14
    Act Density 0.002%

    No Known Activations