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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Handle
    -0.72
    ï¸
    -0.71
    uti
    -0.71
     Answer
    -0.71
     Pros
    -0.69
    hner
    -0.68
     Causes
    -0.68
    chi
    -0.66
     Axis
    -0.66
     Unic
    -0.65
    POSITIVE LOGITS
    growth
    0.78
    bank
    0.69
    WATCH
    0.65
    park
    0.61
    share
    0.60
     reinvest
    0.60
    ONEY
    0.59
    ich
    0.58
    Disclaimer
    0.58
    fuck
    0.57
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.