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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    isition
    -0.66
    resource
    -0.65
    places
    -0.64
    ired
    -0.64
     Grants
    -0.63
    escape
    -0.63
    bucks
    -0.62
     Places
    -0.61
    ota
    -0.59
    cheat
    -0.58
    POSITIVE LOGITS
     flavours
    0.75
    obyl
    0.70
     enthusi
    0.68
    acceptable
    0.68
    forth
    0.67
    rique
    0.67
    auri
    0.66
     unforeseen
    0.65
    bable
    0.65
     millenn
    0.64
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.