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

    Neuronpedia

    INDEX
    Explanations

    historical and geopolitical references

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Arabian
    -0.69
     displays
    -0.68
     emoji
    -0.68
     ballpark
    -0.67
     caution
    -0.67
     notice
    -0.66
     hiber
    -0.66
     drink
    -0.65
     zip
    -0.65
     Dickinson
    -0.64
    POSITIVE LOGITS
    sama
    1.49
    style
    1.33
    based
    1.30
    san
    1.26
    induced
    1.22
    esque
    1.22
    sized
    1.21
    derived
    1.21
    inspired
    1.21
    type
    1.19
    Act Density 0.514%

    No Known Activations