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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    hesis
    -0.78
    ascus
    -0.77
    ailability
    -0.74
    uther
    -0.73
    uctions
    -0.72
    ebus
    -0.70
    ideo
    -0.70
    ittees
    -0.68
    inctions
    -0.66
    alach
    -0.66
    POSITIVE LOGITS
     attached
    0.87
    src
    0.71
    ovember
    0.69
    keep
    0.66
     blindly
    0.62
     redesign
    0.61
    poll
    0.61
     onto
    0.60
     burgers
    0.59
    liam
    0.59
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.