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

    Neuronpedia

    INDEX
    Explanations

    words related to laboratory equipment and processes

    oai_token-act-pair · gpt-3.5-turbo

    references to specific geographic locations or place names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rency
    -0.79
     foremost
    -0.68
     bend
    -0.66
     cannabin
    -0.66
    hyde
    -0.58
    ashtra
    -0.58
     Bangladesh
    -0.57
    inois
    -0.56
     compr
    -0.55
    ftime
    -0.54
    POSITIVE LOGITS
    uries
    0.83
    ãĤ£
    0.81
     Attribution
    0.71
    QL
    0.70
    apons
    0.69
    \-
    0.67
    Byte
    0.66
    andise
    0.66
    ourge
    0.66
    alogy
    0.65
    Act Density 0.206%

    No Known Activations