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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     traged
    -0.71
     Ley
    -0.71
    eneg
    -0.67
     deadliest
    -0.67
     Herz
    -0.66
     Bengal
    -0.65
     dyed
    -0.63
    Ĥª
    -0.62
     Vision
    -0.62
     convincing
    -0.62
    POSITIVE LOGITS
    ocamp
    0.83
    dq
    0.82
    eph
    0.76
    atre
    0.72
    tumblr
    0.70
    ems
    0.68
    ooks
    0.66
    ards
    0.65
    ora
    0.65
    Reviewer
    0.64
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.