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

    Neuronpedia

    INDEX
    Explanations

    legal or technical terms

    oai_token-act-pair · gpt-3.5-turbo

    terms related to legal proceedings and obligations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     mosqu
    -0.78
    senal
    -0.75
     Rebels
    -0.73
    ollah
    -0.70
    lace
    -0.69
    ilater
    -0.67
    choes
    -0.65
    Downloadha
    -0.63
     Hosp
    -0.63
    nesday
    -0.63
    POSITIVE LOGITS
    UTERS
    0.80
    enance
    0.77
    EMBER
    0.72
    女
    0.72
     ns
    0.71
     ILCS
    0.70
    CLASSIFIED
    0.69
    IFE
    0.69
     Bahá
    0.69
    ordinate
    0.69
    Act Density 0.034%

    No Known Activations