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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political and industry-related discussions

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    BuyableInstoreAndOnline
    -0.55
    onne
    -0.53
    uala
    -0.52
     ital
    -0.52
     Abyssal
    -0.52
    entimes
    -0.49
    wealth
    -0.49
     NEC
    -0.48
     Penalty
    -0.48
     Sicily
    -0.47
    POSITIVE LOGITS
    oop
    0.67
    pled
    0.64
    zee
    0.60
    leans
    0.59
    lean
    0.59
    tering
    0.59
    pling
    0.57
    oos
    0.56
    pee
    0.56
    glers
    0.56
    Act Density 0.087%

    No Known Activations