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

    Neuronpedia

    INDEX
    Explanations

    mention of characters in action/adventure stories

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    kefeller
    -0.70
    iband
    -0.66
    Roll
    -0.60
    Cub
    -0.60
    jug
    -0.59
    Ve
    -0.58
    velt
    -0.58
    panel
    -0.58
    ioxide
    -0.58
    Dial
    -0.57
    POSITIVE LOGITS
    ËĪ
    0.65
     Pradesh
    0.62
     Lumpur
    0.60
    rahim
    0.59
     Levant
    0.58
     facto
    0.58
     strangers
    0.58
    uckland
    0.58
    outheast
    0.56
    istrate
    0.56
    Act Density 0.047%

    No Known Activations