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

    Neuronpedia

    INDEX
    Explanations

    words and phrases describing influential and legendary figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atrice
    -0.17
    olg
    -0.15
     Actress
    -0.15
    ohana
    -0.15
    ehir
    -0.14
    اÙĪÙĨ
    -0.14
     жаÑĢ
    -0.14
     packed
    -0.14
    iedo
    -0.14
    ÙĨدگاÙĨ
    -0.14
    POSITIVE LOGITS
     figure
    0.28
     person
    0.25
    人çī©
    0.22
     guy
    0.22
     man
    0.20
     figura
    0.20
     himself
    0.20
     someone
    0.20
     homme
    0.19
     somebody
    0.18
    Act Density 0.430%

    No Known Activations