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

    Neuronpedia

    INDEX
    Explanations

    references to measurements, calculations, and time-related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Wedding
    -0.15
    .AutoComplete
    -0.15
    DataStream
    -0.14
    帽
    -0.14
    olean
    -0.14
    urum
    -0.14
    oste
    -0.14
     Shepherd
    -0.14
     Econom
    -0.13
    ugin
    -0.13
    POSITIVE LOGITS
     lengths
    0.18
    enberg
    0.16
     rounded
    0.16
    -rounded
    0.15
    constants
    0.15
    Round
    0.15
     Rounded
    0.15
    -standard
    0.15
     Units
    0.15
     Length
    0.15
    Act Density 0.096%

    No Known Activations