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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Nicotine
    -0.74
    ansky
    -0.61
    olulu
    -0.60
    hot
    -0.60
    orsche
    -0.60
     rarity
    -0.60
     Yor
    -0.59
    aimon
    -0.59
     circulation
    -0.59
     matter
    -0.59
    POSITIVE LOGITS
     corrid
    0.78
     encour
    0.74
     )]
    0.71
     rall
    0.69
     Volunte
    0.68
     confir
    0.64
    ufact
    0.63
    sbm
    0.62
    paren
    0.62
    DEBUG
    0.62
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.