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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    cffff
    -0.68
    ancial
    -0.68
     retrieving
    -0.68
     hurry
    -0.67
    ilts
    -0.65
     cryptocurrencies
    -0.65
    ierre
    -0.64
     endeavors
    -0.64
    Reviewer
    -0.64
     grades
    -0.63
    POSITIVE LOGITS
    asaki
    0.84
    pole
    0.75
    vic
    0.71
    ocene
    0.70
    enhagen
    0.66
    Fram
    0.66
    minster
    0.63
     Fem
    0.62
     Booth
    0.62
     solicit
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.