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

    Neuronpedia

    INDEX
    Explanations

    terms related to scientific analysis and measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     استنادى
    -0.75
     utafitiHapana
    -0.61
     localObject
    -0.59
     perfons
    -0.57
     podjela
    -0.56
    ēm
    -0.54
    ArrowToggle
    -0.53
     חיצוניים
    -0.53
    ētu
    -0.51
     bezig
    -0.51
    POSITIVE LOGITS
     AssemblyCulture
    0.73
     autorytatywna
    0.63
     دیکھیے
    0.59
    ########.
    0.57
    expandindo
    0.54
    ález
    0.50
     <<<<<<<<<<<<<<
    0.49
    клопе
    0.49
    ble
    0.49
     onCancelled
    0.48
    Act Density 1.521%

    No Known Activations