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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    inoa
    -0.85
    ortunate
    -0.77
    ected
    -0.67
    paralleled
    -0.66
    olve
    -0.66
    idge
    -0.65
    chell
    -0.64
    abbit
    -0.63
    terday
    -0.62
    anamo
    -0.62
    POSITIVE LOGITS
    £ı
    0.80
    HOU
    0.70
    aceae
    0.69
    sbm
    0.69
    spir
    0.68
    Ń
    0.67
    house
    0.66
    )]
    0.65
     kisses
    0.64
     GIF
    0.64
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.