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

    Neuronpedia

    INDEX
    Explanations

    quotes and passages from religious texts

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    tsky
    -0.90
    owicz
    -0.78
     Wilde
    -0.74
     Freud
    -0.74
    coe
    -0.72
    iewicz
    -0.70
    imov
    -0.67
     Helsinki
    -0.67
    anchester
    -0.67
    ormal
    -0.67
    POSITIVE LOGITS
     unto
    1.06
    areth
    1.05
     ye
    0.96
    joice
    0.96
     Judah
    0.94
    estial
    0.94
     Pharaoh
    0.91
     ×
    0.91
     LORD
    0.91
     brethren
    0.90
    Act Density 0.178%

    No Known Activations