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

    Neuronpedia

    INDEX
    Explanations

    sentences related to personal experiences and reflections

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    They
    -0.70
    )</
    -0.68
    idates
    -0.66
    Their
    -0.65
    ãħĭ
    -0.63
    Lot
    -0.58
     Says
    -0.57
    Alert
    -0.57
    eds
    -0.56
     doesnt
    -0.56
    POSITIVE LOGITS
     myself
    1.88
     my
    1.49
     MY
    0.90
     My
    0.85
    My
    0.82
     ourselves
    0.81
    my
    0.79
     blogging
    0.71
     admittedly
    0.69
     naïve
    0.66
    Act Density 1.005%

    No Known Activations