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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    utterstock
    -0.70
    ghan
    -0.70
    pak
    -0.69
    iHUD
    -0.64
    change
    -0.64
     supervised
    -0.63
    Gam
    -0.63
    izon
    -0.63
     curs
    -0.63
    form
    -0.62
    POSITIVE LOGITS
    DOWN
    0.76
    hops
    0.67
     Survive
    0.66
     Brother
    0.65
    itty
    0.65
     Pieces
    0.65
     Nightmares
    0.63
    ername
    0.62
    anny
    0.62
    estones
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.