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

    Neuronpedia

    INDEX
    Explanations

    references to specific geographic locations

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the suffix "aya"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    auld
    -0.89
    ipeg
    -0.89
    yright
    -0.86
    itude
    -0.78
    ancial
    -0.76
    rodu
    -0.76
    iculture
    -0.76
    icultural
    -0.74
    asses
    -0.72
    found
    -0.72
    POSITIVE LOGITS
    ñ
    0.84
     Yose
    0.81
    eva
    0.75
    udo
    0.74
    uga
    0.74
     Gupta
    0.72
     Palace
    0.72
     Gaz
    0.69
    iba
    0.68
     Clause
    0.68
    Act Density 0.025%

    No Known Activations