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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    regor
    -0.75
    ecause
    -0.74
     OnePlus
    -0.71
    abor
    -0.71
     Hours
    -0.70
    odox
    -0.67
    xit
    -0.67
    utic
    -0.67
    uries
    -0.66
    issions
    -0.66
    POSITIVE LOGITS
     Valhalla
    0.69
     flashback
    0.65
     sailor
    0.65
    seed
    0.64
     animosity
    0.64
    ched
    0.64
     opponent
    0.64
     selector
    0.64
    ris
    0.63
     adversary
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.