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

    Neuronpedia

    INDEX
    Explanations

    phrases that denote uncertainty or variability in experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     iParam
    -0.52
     ferdig
    -0.52
     californ
    -0.50
    لاثة
    -0.49
    ReactDOM
    -0.49
    TProtocol
    -0.49
    ServerSocket
    -0.48
    unjang
    -0.48
    ='#
    -0.47
     #{
    -0.47
    POSITIVE LOGITS
    Sometimes
    1.30
     Sometimes
    1.27
     sometimes
    1.25
    sometimes
    1.21
     parfois
    0.95
     quelquefois
    0.94
     бывает
    0.94
     manchmal
    0.93
     oftentimes
    0.93
     veces
    0.88
    Act Density 0.105%

    No Known Activations