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

    Neuronpedia

    INDEX
    Explanations

    chess move descriptions

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    lycer
    -0.85
    isky
    -0.81
    icipated
    -0.81
     overhead
    -0.81
    ikuman
    -0.76
     clicks
    -0.76
     heaviest
    -0.76
     ingred
    -0.75
    conserv
    -0.74
    Cong
    -0.74
    POSITIVE LOGITS
    ionage
    1.02
    tainment
    0.91
    ploy
    0.87
    911
    0.85
    hyde
    0.85
    ruction
    0.84
    ird
    0.84
    Sah
    0.82
     Tah
    0.80
     Monaco
    0.79
    Act Density 4.237%

    No Known Activations