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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     SHAR
    -0.66
    thought
    -0.65
    avorite
    -0.65
    plates
    -0.65
    strength
    -0.64
     FANT
    -0.63
    plate
    -0.62
    shadow
    -0.61
    Storm
    -0.60
     Ballistic
    -0.60
    POSITIVE LOGITS
    arity
    0.73
    opian
    0.71
     Cosponsors
    0.67
     Fiat
    0.65
    ogle
    0.62
     environment
    0.61
    ulz
    0.61
    ually
    0.61
    intendo
    0.59
    ido
    0.58
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.