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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    lessness
    -0.72
     amounts
    -0.69
     raining
    -0.69
     earthqu
    -0.68
    artifacts
    -0.66
     determin
    -0.66
     deleg
    -0.65
     reluct
    -0.65
     roles
    -0.64
     respecting
    -0.63
    POSITIVE LOGITS
    yip
    0.95
    owler
    0.80
    ventus
    0.74
    zl
    0.73
    é¾įå
    0.73
    bold
    0.73
    ulton
    0.72
    fm
    0.72
    utm
    0.71
    ight
    0.71
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.