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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    deen
    -0.81
     DPS
    -0.63
     Countdown
    -0.61
    erella
    -0.61
    ines
    -0.59
    TPPStreamerBot
    -0.58
    rior
    -0.58
     haircut
    -0.57
     [&
    -0.56
     rooting
    -0.56
    POSITIVE LOGITS
    aughs
    0.79
    uay
    0.69
    sterdam
    0.67
     apologised
    0.66
    ugal
    0.64
    apego
    0.63
     Izan
    0.63
    had
    0.61
    avour
    0.60
    atu
    0.60
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.