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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Nare
    -0.75
     trough
    -0.69
     Lama
    -0.66
     poppy
    -0.66
    aniel
    -0.63
    ced
    -0.63
    pite
    -0.62
    nered
    -0.62
     dil
    -0.61
     Shal
    -0.61
    POSITIVE LOGITS
    andowski
    0.76
    ãĤ¨ãĥ«
    0.68
    artifacts
    0.67
     Explosion
    0.62
    redients
    0.62
    soDeliveryDate
    0.61
    assis
    0.60
    Assembly
    0.60
    û
    0.59
     NCT
    0.59
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.