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

    Neuronpedia

    INDEX
    Explanations

    links or calls to action in the text

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    venge
    -0.61
    otyp
    -0.59
    ogram
    -0.59
    vernment
    -0.58
    otype
    -0.58
    mouth
    -0.57
    inals
    -0.57
     reused
    -0.56
    Percent
    -0.55
    rete
    -0.55
    POSITIVE LOGITS
     www
    0.96
     HERE
    0.92
     http
    0.87
     https
    0.84
     our
    0.79
     here
    0.76
     links
    0.72
     Consortium
    0.71
     WW
    0.71
    ://
    0.71
    Act Density 0.109%

    No Known Activations