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

    Neuronpedia

    INDEX
    Explanations

    phrases related to financial matters or corruption

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate a hierarchical structure or ranking

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    onyms
    -0.73
    aren
    -0.66
     goblins
    -0.66
    aver
    -0.65
    DERR
    -0.65
    ocamp
    -0.64
    nces
    -0.63
    arten
    -0.63
    asel
    -0.62
     gust
    -0.62
    POSITIVE LOGITS
     Secondary
    0.73
    Chain
    0.72
    ģĸ
    0.69
    chain
    0.68
     equation
    0.67
     chain
    0.67
    tein
    0.65
     society
    0.64
    oried
    0.63
    */(
    0.60
    Act Density 0.515%

    No Known Activations