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

    Neuronpedia

    INDEX
    Explanations

    keywords related to lists or collections of items

    oai_token-act-pair · gpt-3.5-turbo

    the word "list" in various forms and contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Aber
    -0.57
     stride
    -0.55
     Gibbs
    -0.55
     Fine
    -0.55
    selves
    -0.54
     Galile
    -0.54
    bole
    -0.54
     Depths
    -0.54
     Gaul
    -0.53
     merry
    -0.53
    POSITIVE LOGITS
    icles
    1.25
    icle
    1.22
    ening
    1.22
    ener
    1.17
    erv
    1.15
    eners
    1.15
    enable
    0.96
    lessness
    0.89
     comprehens
    0.87
    ings
    0.83
    Act Density 0.070%

    No Known Activations