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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Cooke
    -0.75
    Buzz
    -0.67
    ongs
    -0.65
    geist
    -0.64
    hop
    -0.64
     Cosmos
    -0.62
    SF
    -0.61
    âĹ¼
    -0.61
    Chain
    -0.61
     Chain
    -0.61
    POSITIVE LOGITS
    thal
    0.74
    tery
    0.66
    gaming
    0.65
    adium
    0.64
    ansom
    0.64
    ilitarian
    0.64
    emn
    0.63
    oker
    0.61
    idia
    0.61
    rection
    0.60
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.