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

    Neuronpedia

    INDEX
    Explanations

    HTML/XML tags, attributes, and their configurations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    RAP
    -0.15
     favour
    -0.15
     Monthly
    -0.15
    865
    -0.15
     favor
    -0.14
    çĽ
    -0.14
    undry
    -0.14
    Selectors
    -0.14
     favors
    -0.14
    æĬĢ
    -0.13
    POSITIVE LOGITS
    0.30
          ↵
    0.18
    0.18
    0.18
    218
    0.18
    229
    0.17
    illard
    0.17
     Hayward
    0.17
    239
    0.17
    231
    0.17
    Act Density 0.296%

    No Known Activations