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

    Neuronpedia

    INDEX
    Explanations

    action verbs that indicate construction or arrangement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Gamble
    -0.80
    assies
    -0.67
     Pok
    -0.67
     Hurricanes
    -0.65
    cot
    -0.64
     Cheong
    -0.63
    ierre
    -0.63
    ouf
    -0.63
     Strait
    -0.62
    cott
    -0.62
    POSITIVE LOGITS
     by
    0.89
     exclusively
    0.87
     solely
    0.87
     prominently
    0.85
     BY
    0.83
     collabor
    0.79
     expressly
    0.78
    inel
    0.75
     concurrently
    0.73
     upon
    0.73
    Act Density 0.142%

    No Known Activations