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

    Neuronpedia

    INDEX
    Explanations

    the name "Morelli"

    oai_token-act-pair · gpt-3.5-turbo

    repeated use of the name "Lilli"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rooms
    -0.75
    mal
    -0.74
    LESS
    -0.72
    ifiers
    -0.67
     Alive
    -0.66
    grounds
    -0.66
    lines
    -0.66
    binary
    -0.65
     Corpus
    -0.65
    rush
    -0.65
    POSITIVE LOGITS
    otti
    1.12
    quist
    0.94
    lli
    0.92
    zzi
    0.92
    zzle
    0.90
    zzo
    0.90
    oyd
    0.89
    oti
    0.89
    ptin
    0.88
    orno
    0.87
    Act Density 0.006%

    No Known Activations