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

    Neuronpedia

    INDEX
    Explanations

    names of characters and locations from a specific fictional series

    oai_token-act-pair · gpt-3.5-turbo

    character names from a specific TV series

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itud
    -0.78
    trak
    -0.75
    score
    -0.73
    isconsin
    -0.72
    EPA
    -0.69
    iba
    -0.68
    lli
    -0.66
    itudes
    -0.64
    oard
    -0.63
    izu
    -0.63
    POSITIVE LOGITS
     Lann
    1.60
     Bolton
    1.18
     Stark
    1.12
     Thrones
    1.10
     Wester
    1.08
     Targ
    1.05
     Robb
    0.92
     Archdemon
    0.85
     compr
    0.84
     tyr
    0.82
    Act Density 0.027%

    No Known Activations