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

    Neuronpedia

    INDEX
    Explanations

    references to specific locations, particularly cities

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     misconduct
    -0.76
     regulator
    -0.75
     Enhancement
    -0.75
    ¿½
    -0.71
     Submission
    -0.71
     retracted
    -0.71
    illus
    -0.69
    yss
    -0.69
    ensor
    -0.68
     captcha
    -0.68
    POSITIVE LOGITS
     downtown
    1.41
     suburb
    1.37
     inland
    1.31
     locals
    1.31
     Downtown
    1.29
     tourist
    1.28
     cities
    1.26
     towns
    1.26
     geography
    1.25
     suburbs
    1.24
    Act Density 0.939%

    No Known Activations