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

    Neuronpedia

    INDEX
    Explanations

    phrases related to problem-solving and decision-making

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    nor
    -0.65
     accompanied
    -0.64
    ONG
    -0.62
     Belief
    -0.59
    eed
    -0.58
    court
    -0.58
    udos
    -0.57
    interrupted
    -0.57
    ibaba
    -0.57
    PET
    -0.57
    POSITIVE LOGITS
     out
    1.17
     prominently
    0.83
     OUT
    0.83
     skating
    0.81
     things
    0.79
     something
    0.74
     trig
    0.72
    out
    0.70
     how
    0.70
     outs
    0.68
    Act Density 0.025%

    No Known Activations