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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     perspect
    -0.69
    ties
    -0.66
    selves
    -0.65
     Binary
    -0.65
    ievers
    -0.64
     ]
    -0.64
     Disp
    -0.64
     convers
    -0.63
     horizont
    -0.61
     dissolved
    -0.59
    POSITIVE LOGITS
    ngth
    0.82
    asus
    0.75
    avorite
    0.73
    ANI
    0.73
    ungle
    0.73
    ħĭ
    0.70
    ongyang
    0.68
    ems
    0.68
    aga
    0.67
    urden
    0.66
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.