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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    rete
    -0.89
    llo
    -0.82
    onde
    -0.78
     Pamela
    -0.71
     Venus
    -0.71
     Ramsay
    -0.70
     Minerva
    -0.69
     Lily
    -0.67
    ueless
    -0.67
     Machina
    -0.67
    POSITIVE LOGITS
     checkpoints
    0.72
    intel
    0.70
    competitive
    0.70
     choke
    0.69
     peanuts
    0.69
    gotten
    0.66
     slack
    0.66
     sting
    0.65
     dissent
    0.63
     pinch
    0.62
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.