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

    Neuronpedia

    INDEX
    Explanations

    the name "Tal" followed by a number, with varying degrees of activation for different numbers

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Tal" across various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lihood
    -0.77
    EEE
    -0.75
    ï¸
    -0.67
    âķIJ
    -0.67
     Veronica
    -0.67
    ãĥĩãĤ£
    -0.67
    vernment
    -0.66
     Hearts
    -0.65
    ullivan
    -0.64
     largeDownload
    -0.63
    POSITIVE LOGITS
    isman
    1.10
    iban
    1.01
    mud
    0.91
    aga
    0.89
    imony
    0.86
    ented
    0.85
    ison
    0.84
    uder
    0.82
    ues
    0.81
    ibur
    0.81
    Act Density 0.005%

    No Known Activations