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

    Neuronpedia

    INDEX
    Explanations

    numbers of entities mentioned in the text

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    Secure
    -0.55
    RED
    -0.54
     srfAttach
    -0.54
    CLE
    -0.53
    cipled
    -0.53
    itech
    -0.52
    ĺħ
    -0.52
    HY
    -0.52
    risome
    -0.51
    lov
    -0.50
    POSITIVE LOGITS
    imester
    0.87
     stages
    0.74
     paragraphs
    0.69
     iterations
    0.68
    ttle
    0.68
    teen
    0.67
     phases
    0.63
     months
    0.62
     chapters
    0.62
     episodes
    0.61
    Act Density 10.328%

    No Known Activations