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

    Neuronpedia

    INDEX
    Explanations

    references to operational or procedural contexts, especially related to compliance or rules

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hai
    -0.15
    ices
    -0.14
    578
    -0.14
    keley
    -0.14
    ching
    -0.14
    oders
    -0.14
    rike
    -0.14
    errick
    -0.14
     bridge
    -0.14
    tsx
    -0.14
    POSITIVE LOGITS
    .nextToken
    0.15
    Ä°Y
    0.15
     pev
    0.15
    _dicts
    0.15
     Král
    0.14
    kova
    0.14
    IPH
    0.14
     Claus
    0.14
    insky
    0.14
    \Collections
    0.14
    Act Density 0.001%

    No Known Activations