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

    Neuronpedia

    INDEX
    Explanations

    terms related to legal proceedings and official documentation

    oai_token-act-pair · gpt-3.5-turbo

    prominent names and figures associated with various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     McGregor
    -0.78
     Abby
    -0.77
    inho
    -0.76
     McConnell
    -0.75
    pport
    -0.74
    abby
    -0.73
    regor
    -0.73
     Mech
    -0.73
    orf
    -0.72
    Buff
    -0.72
    POSITIVE LOGITS
     Se
    2.51
     se
    2.00
    Se
    1.96
    se
    1.83
    Seg
    1.73
    Sel
    1.72
     SE
    1.62
     Sel
    1.60
    SE
    1.56
     Seal
    1.21
    Act Density 0.209%

    No Known Activations