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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    gel
    -0.89
    earances
    -0.86
    endor
    -0.85
    rien
    -0.84
    milo
    -0.84
    pire
    -0.83
    rious
    -0.80
    pots
    -0.76
    burgh
    -0.76
    rift
    -0.75
    POSITIVE LOGITS
     nexus
    0.78
    ATH
    0.67
     liability
    0.66
     DL
    0.66
     Battery
    0.65
     ______
    0.63
     assembly
    0.62
     kickoff
    0.62
     secondly
    0.61
     battery
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.