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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    aque
    -0.85
     Flavoring
    -0.82
    pson
    -0.81
    acs
    -0.80
    ittees
    -0.78
    ores
    -0.78
    acio
    -0.78
    eport
    -0.71
    ersed
    -0.71
    formance
    -0.71
    POSITIVE LOGITS
    cept
    0.65
     pollen
    0.63
     prod
    0.61
     logically
    0.59
     pleas
    0.59
     solicitor
    0.59
    ogyn
    0.58
     grossly
    0.58
     bir
    0.56
     utilitarian
    0.56
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.