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

    Neuronpedia

    INDEX
    Explanations

    adverbs, particularly those ending in 'ly' and related to enhancing or limiting actions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "bas" and its variations related to various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    WIND
    -0.73
     Oaks
    -0.69
    WORK
    -0.68
     Ack
    -0.66
    OPE
    -0.66
    markets
    -0.62
    kefeller
    -0.62
    APE
    -0.62
     Heller
    -0.62
    istor
    -0.61
    POSITIVE LOGITS
    ility
    0.88
    sembly
    0.87
    emen
    0.83
    uity
    0.82
    iliate
    0.78
    ements
    0.78
     ig
    0.77
    cule
    0.75
    inally
    0.75
    imet
    0.73
    Act Density 0.016%

    No Known Activations