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

    Neuronpedia

    INDEX
    Explanations

    mentions of the word "ala" combined with numbers indicating some sort of significance or hierarchy

    oai_token-act-pair · gpt-3.5-turbo

    references to the subject of "malay."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    manship
    -0.98
    liness
    -0.92
    ly
    -0.92
    lies
    -0.87
    LY
    -0.87
    land
    -0.82
    lers
    -0.79
    lines
    -0.78
    lands
    -0.77
    dit
    -0.75
    POSITIVE LOGITS
    ibaba
    1.02
    uthor
    0.93
    isa
    0.84
    qua
    0.84
    ika
    0.83
    emia
    0.82
    ise
    0.82
    ised
    0.77
    istical
    0.77
    velength
    0.76
    Act Density 0.039%

    No Known Activations