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

    Neuronpedia

    INDEX
    Explanations

    quoted statements within a text

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     arch
    -0.78
     adjud
    -0.72
     prelim
    -0.70
     favor
    -0.70
     repro
    -0.70
     listed
    -0.69
     disappro
    -0.68
     scheduled
    -0.68
     separated
    -0.68
     vault
    -0.68
    POSITIVE LOGITS
    We
    1.56
    Our
    1.48
    They
    1.45
    It
    1.45
    There
    1.45
    Everybody
    1.44
    Everything
    1.40
    Nobody
    1.40
    I
    1.38
    People
    1.37
    Act Density 0.326%

    No Known Activations