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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, specifically names of individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals, particularly those named Braz and Deborah

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arium
    -0.91
     Sabha
    -0.85
    nery
    -0.82
    urtles
    -0.79
    oldemort
    -0.77
    apore
    -0.77
    Parent
    -0.74
    elia
    -0.73
    enza
    -0.73
    ierra
    -0.72
    POSITIVE LOGITS
    lain
    0.87
     Braz
    0.81
     ank
    0.74
    tons
    0.71
    hyde
    0.70
    maid
    0.68
     microphones
    0.68
    levard
    0.64
     medi
    0.63
     horizont
    0.63
    Act Density 0.018%

    No Known Activations