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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating hierarchical or positional relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tl
    -0.16
     Treasure
    -0.16
    tb
    -0.15
    .Parcelable
    -0.15
    .routes
    -0.15
    tem
    -0.15
    á¿ĸ
    -0.14
    rels
    -0.14
    801
    -0.14
    reater
    -0.14
    POSITIVE LOGITS
    ertino
    0.21
    iveau
    0.16
     stairs
    0.16
    ystack
    0.15
     stocks
    0.15
    ully
    0.15
    azole
    0.15
    onds
    0.15
     heap
    0.14
    cales
    0.14
    Act Density 0.035%

    No Known Activations