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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the beginning of an action or process

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     entirety
    -0.73
    obi
    -0.71
    omb
    -0.68
    icol
    -0.64
    athed
    -0.62
    ingly
    -0.61
    mens
    -0.61
    ighth
    -0.61
    illard
    -0.59
    airy
    -0.59
    POSITIVE LOGITS
     anew
    1.02
    ŃĶ
    0.82
     behaving
    0.79
     raining
    0.74
     dating
    0.74
    nings
    0.73
     experimenting
    0.73
     hemor
    0.72
     noticing
    0.72
     researching
    0.71
    Act Density 0.068%

    No Known Activations