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

    Neuronpedia

    INDEX
    Explanations

    acronyms related to technology

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific entity or product labeled as "AR."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hower
    -0.82
    éĹĺ
    -0.82
    ãĤ´ãĥ³
    -0.76
    ãĥij
    -0.76
     Pelosi
    -0.75
    ãĥ¼ãĥĨãĤ£
    -0.75
    ãĥ¯
    -0.73
     Mercury
    -0.71
    ãĥĩãĤ£
    -0.69
    erella
    -0.67
    POSITIVE LOGITS
    ansas
    0.91
    ENA
    0.91
    RR
    0.87
    OUND
    0.82
    RL
    0.80
    RAY
    0.76
    IAN
    0.75
    IZ
    0.74
     Rahman
    0.74
    ELY
    0.73
    Act Density 0.004%

    No Known Activations