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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ratulations
    -0.72
    idate
    -0.71
    sec
    -0.71
    href
    -0.68
    PsyNetMessage
    -0.68
    ulty
    -0.68
    rand
    -0.67
    orno
    -0.66
    blance
    -0.65
    geries
    -0.65
    POSITIVE LOGITS
     abroad
    0.73
    ocating
    0.70
    INESS
    0.66
     afar
    0.64
     ashore
    0.63
     underestimated
    0.62
    OCK
    0.62
    MG
    0.61
    OT
    0.61
    OL
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.