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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    wired
    -0.67
    work
    -0.62
     truths
    -0.62
     transcripts
    -0.61
    .","
    -0.59
    email
    -0.58
    htaking
    -0.57
    leader
    -0.57
     successes
    -0.56
    helial
    -0.56
    POSITIVE LOGITS
    tsky
    0.78
    iott
    0.68
     gravy
    0.67
     ABV
    0.66
     coating
    0.66
     Constantin
    0.65
    isin
    0.64
    agall
    0.63
    age
    0.63
    enegger
    0.63
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.