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

    Neuronpedia

    INDEX
    Explanations

    comparisons involving numerical multiples or increases

    oai_token-act-pair · gpt-3.5-turbo

    instances of a specific token or concept repeated multiple times

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    PLA
    -0.82
    RAW
    -0.75
    AMA
    -0.72
     Leilan
    -0.70
    ETF
    -0.68
    GGGG
    -0.68
    ARA
    -0.67
    DD
    -0.64
    ND
    -0.64
    ////////
    -0.63
    POSITIVE LOGITS
     usual
    0.99
     average
    0.90
     amount
    0.87
    oples
    0.84
     fastest
    0.80
     same
    0.79
     extent
    0.77
     busiest
    0.76
     thickness
    0.75
     country
    0.74
    Act Density 0.098%

    No Known Activations