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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, particularly names and places

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     resil
    -0.69
    ongyang
    -0.62
     shenan
    -0.61
     magnification
    -0.61
     conspicuous
    -0.59
     proble
    -0.58
    behind
    -0.58
    perty
    -0.57
     fundament
    -0.56
     cessation
    -0.55
    POSITIVE LOGITS
    iewicz
    0.95
    ieri
    0.83
    ux
    0.81
    ovich
    0.78
    cia
    0.77
     Abbey
    0.76
    ews
    0.74
    coni
    0.74
    gian
    0.73
    baum
    0.73
    Act Density 0.157%

    No Known Activations