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

    Neuronpedia

    INDEX
    Explanations

    expressions indicating frustration and dissatisfaction

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     makro
    -0.86
     kask
    -0.85
     karton
    -0.81
     kade
    -0.77
     silikon
    -0.77
     kön
    -0.74
     etui
    -0.71
     elek
    -0.71
     moza
    -0.71
     alkoh
    -0.71
    POSITIVE LOGITS
     being
    0.47
    ABUL
    0.45
     hearing
    0.43
     dealing
    0.43
     pretending
    0.42
     blowing
    0.42
     playing
    0.42
     padx
    0.42
     antimony
    0.41
     chasing
    0.41
    Act Density 0.157%

    No Known Activations