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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     lying
    -0.64
     admitting
    -0.63
     esteem
    -0.62
     muster
    -0.62
     behaving
    -0.61
     restraining
    -0.61
     erect
    -0.61
     restraint
    -0.60
     refuse
    -0.60
    reads
    -0.59
    POSITIVE LOGITS
     Pwr
    0.87
    bat
    0.81
    psc
    0.79
    kaya
    0.79
    utions
    0.79
     Gleaming
    0.74
     Puppet
    0.71
    onday
    0.71
    Ń·
    0.70
    ©
    0.70
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.