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

    Neuronpedia

    INDEX
    Explanations

    numerical values formatted as dollar amounts

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     Univers
    -0.63
     tremend
    -0.62
     bailed
    -0.62
     boun
    -0.58
    Ô
    -0.58
     celebrated
    -0.57
     Finger
    -0.57
    ĸļ
    -0.56
     Bere
    -0.56
     happ
    -0.56
    POSITIVE LOGITS
    ax
    0.78
    66
    0.76
    uez
    0.74
    39
    0.74
    36
    0.73
    apter
    0.73
    ophers
    0.72
    ollo
    0.72
    76
    0.72
    79
    0.72
    Act Density 0.045%

    No Known Activations