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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    clone
    -0.63
    ENTION
    -0.63
    bed
    -0.61
    é»Ĵ
    -0.60
     âĢº
    -0.60
     along
    -0.60
    theless
    -0.59
     passionately
    -0.59
    chest
    -0.58
    lust
    -0.58
    POSITIVE LOGITS
    alach
    0.89
    ascript
    0.88
    nown
    0.76
    espie
    0.73
    enegger
    0.71
     Attribution
    0.71
    gypt
    0.71
    irds
    0.66
    inav
    0.64
     Logic
    0.64
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.