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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    dden
    -0.75
    cius
    -0.73
    lé
    -0.69
    ral
    -0.68
    ussen
    -0.68
    nda
    -0.68
    ament
    -0.66
    uca
    -0.66
    olen
    -0.65
    ients
    -0.64
    POSITIVE LOGITS
    bugs
    0.71
    arium
    0.69
    ãĤ¸
    0.66
    advertising
    0.65
    agents
    0.64
     indisp
    0.64
    quote
    0.63
     Bugs
    0.62
    addons
    0.61
     Slay
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.