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

    Neuronpedia

    INDEX
    Explanations

    references to specific events or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    تقاوى
    -0.95
    ^(@)
    -0.89
     الحره
    -0.86
    Rüyada
    -0.83
    >';
    -0.71
    saraba
    -0.69
    neſs
    -0.68
    uxxxx
    -0.67
     становника
    -0.66
     \\
    -0.64
    POSITIVE LOGITS
     instantly
    0.59
    Cyfeiriadau
    0.58
    h
    0.55
     prominently
    0.54
     komple
    0.52
     furiously
    0.51
     nakalista
    0.51
     automaticamente
    0.50
    Configurator
    0.49
     bek
    0.49
    Act Density 1.437%

    No Known Activations