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

    Neuronpedia

    INDEX
    Explanations

    terms related to theoretical concepts and modeling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ujednoznacz
    -0.60
    Geplaatst
    -0.58
     CURIAM
    -0.54
    newArrayList
    -0.53
    setUrl
    -0.52
     Brava
    -0.52
    :]
    -0.51
    ystis
    -0.49
    Whatever
    -0.47
    endregion
    -0.47
    POSITIVE LOGITS
     fore
    0.84
     pile
    0.82
     piled
    0.82
     heights
    0.78
     height
    0.77
     heap
    0.73
     piling
    0.72
     HEIGHT
    0.70
     weighing
    0.69
     kurios
    0.67
    Act Density 0.094%

    No Known Activations