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

    Neuronpedia

    INDEX
    Explanations

    phrases related to regularity or consistency

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "regular" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Sov
    -0.77
    UST
    -0.76
    lda
    -0.75
    Drug
    -0.71
    IDA
    -0.68
    IRO
    -0.68
    FG
    -0.66
    Cub
    -0.65
    arta
    -0.64
    Attorney
    -0.64
    POSITIVE LOGITS
    ity
    1.19
    ised
    1.06
    isation
    1.01
    isations
    0.96
    cy
    0.95
    ization
    0.92
    ises
    0.90
    ITY
    0.89
     occurrence
    0.87
    izations
    0.86
    Act Density 0.016%

    No Known Activations