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

    Neuronpedia

    INDEX
    Explanations

    words associated with spoiling or related actions

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    囗
    -0.72
     blindness
    -0.72
    SwingConstants
    -0.71
    endphp
    -0.71
    writerow
    -0.71
    knecht
    -0.68
    }")
    -0.67
    escence
    -0.67
     Polres
    -0.67
    uksen
    -0.66
    POSITIVE LOGITS
     Spo
    1.41
     spo
    1.30
     spoil
    1.24
     spore
    1.23
     spoiling
    1.23
    spo
    1.17
    Spo
    1.16
     SPO
    1.14
     spores
    1.09
     spoils
    1.09
    Act Density 0.009%

    No Known Activations