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

    Neuronpedia

    INDEX
    Explanations

    references to fleeing or escaping

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    essee
    -0.83
    lease
    -0.66
    wcsstore
    -0.63
    ature
    -0.63
    arist
    -0.62
    ventures
    -0.62
     MFT
    -0.61
     stead
    -0.60
     Quadro
    -0.60
    Deal
    -0.60
    POSITIVE LOGITS
     captivity
    0.74
     persecution
    0.70
    ROR
    0.69
     unsc
    0.68
    ce
    0.68
    ring
    0.66
     Torment
    0.64
     fearing
    0.64
     peacefully
    0.64
    itably
    0.64
    Act Density 0.078%

    No Known Activations