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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    minist
    -0.75
    warning
    -0.74
    psons
    -0.74
    querque
    -0.70
    danger
    -0.69
    vernment
    -0.67
    ilib
    -0.64
    angles
    -0.64
     Adventures
    -0.63
    anton
    -0.62
    POSITIVE LOGITS
    kefeller
    0.77
    Num
    0.71
     recharge
    0.69
    Magikarp
    0.69
    hner
    0.67
    Fit
    0.65
    atile
    0.65
    uilt
    0.63
     computing
    0.62
     Chung
    0.62
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.