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

    Neuronpedia

    INDEX
    Explanations

    words related to freedom, permission, and expression

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    quickShipAvailable
    -0.69
    soDeliveryDate
    -0.63
    Roy
    -0.58
    hur
    -0.57
    ccording
    -0.57
    Dur
    -0.56
    grain
    -0.56
     millenn
    -0.54
    IJ
    -0.53
    Hur
    -0.53
    POSITIVE LOGITS
     roam
    0.90
     explore
    0.89
     indulge
    0.89
     pursue
    0.83
     choose
    0.82
     speculate
    0.80
     participate
    0.78
     submit
    0.78
     negotiate
    0.78
     take
    0.76
    Act Density 10.810%

    No Known Activations