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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    cles
    -0.73
    ngth
    -0.67
    apons
    -0.67
    anim
    -0.66
    close
    -0.66
     enrichment
    -0.65
    ozyg
    -0.64
    lling
    -0.64
     unlocked
    -0.64
     exile
    -0.64
    POSITIVE LOGITS
     DT
    0.74
    awks
    0.64
    lease
    0.63
     Prel
    0.61
     Wei
    0.61
     Sounders
    0.61
     Seller
    0.60
     Loving
    0.60
     Streets
    0.59
     Tooth
    0.59
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.