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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Sav
    -0.78
    rio
    -0.76
    IU
    -0.75
    DragonMagazine
    -0.74
    OSE
    -0.71
    ATA
    -0.70
    Tier
    -0.69
    èĢħ
    -0.69
    ISH
    -0.67
    ailable
    -0.67
    POSITIVE LOGITS
    merga
    0.71
     Lyme
    0.71
    iban
    0.66
     Princ
    0.62
     Guant
    0.62
    FTWARE
    0.60
     Furious
    0.60
     Zeit
    0.60
     airstrikes
    0.59
     Emails
    0.59
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.