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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ankind
    -0.70
     Starfleet
    -0.68
    nered
    -0.68
    runtime
    -0.65
    acebook
    -0.65
    CHQ
    -0.64
    ussia
    -0.64
    warn
    -0.62
    isations
    -0.61
    isable
    -0.61
    POSITIVE LOGITS
    UGE
    0.84
     VIDEOS
    0.80
    WARE
    0.73
    OUT
    0.70
    ISO
    0.68
    TON
    0.67
    PF
    0.66
    METHOD
    0.65
     Cotton
    0.62
    IPS
    0.62
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.