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

    Neuronpedia

    INDEX
    Explanations

    terms related to educational qualifications or certifications

    oai_token-act-pair · gpt-3.5-turbo

    references to government regulations or standards

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lihood
    -0.83
    hold
    -0.81
    cies
    -0.76
    oÄŁ
    -0.73
    gren
    -0.69
    lla
    -0.68
    chel
    -0.67
    lies
    -0.67
    deals
    -0.64
    under
    -0.63
    POSITIVE LOGITS
    asper
    0.88
    ARD
    0.86
    AMS
    0.82
    ATS
    0.78
    ORGE
    0.78
    INTON
    0.78
    ategory
    0.76
    ATES
    0.73
    ADE
    0.73
    SE
    0.72
    Act Density 0.041%

    No Known Activations