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

    Neuronpedia

    INDEX
    Explanations

    references to electronic devices

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals, particularly the name "Gad" and variations of it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥĺ
    -0.79
    xual
    -0.75
    antha
    -0.70
    ãĥ³ãĤ¸
    -0.69
    CEPT
    -0.68
    ASON
    -0.65
    charged
    -0.64
    ãĥīãĥ©
    -0.63
    BSD
    -0.63
    RT
    -0.62
    POSITIVE LOGITS
    iesel
    1.04
    iation
    0.91
    iant
    0.91
    rial
    0.89
    roid
    0.89
    icular
    0.86
    iated
    0.85
    rian
    0.85
    roxy
    0.84
    icative
    0.84
    Act Density 0.051%

    No Known Activations