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

    Neuronpedia

    INDEX
    Explanations

    arabic numerals

    oai_token-act-pair · gpt-3.5-turbo

    references to varying forms of "AR" which likely pertains to assessments, ratings, or statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tons
    -0.82
     Mercury
    -0.79
    ĸļ
    -0.75
     Rasmussen
    -0.75
     Vide
    -0.73
    phis
    -0.72
    ãĤ´ãĥ³
    -0.71
    ãĥīãĥ©
    -0.69
    vous
    -0.69
     Europa
    -0.68
    POSITIVE LOGITS
    RR
    0.98
    ENA
    0.96
    ILY
    0.96
    MY
    0.91
    AR
    0.91
    ELY
    0.90
    IAN
    0.90
    IES
    0.88
    RAG
    0.88
    IAL
    0.83
    Act Density 0.007%

    No Known Activations