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

    Neuronpedia

    INDEX
    Explanations

    phrases related to a lack of response or refusal to comment

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a lack of response or comments from various entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cabin
    -0.73
     Sinai
    -0.69
    tail
    -0.68
    hab
    -0.68
    gran
    -0.66
    ppo
    -0.62
    cephal
    -0.61
    relative
    -0.61
    course
    -0.61
    VALUE
    -0.61
    POSITIVE LOGITS
    ysis
    0.98
     ado
    0.81
    ariat
    0.80
    ittal
    0.74
     queries
    0.74
     comment
    0.73
     acknow
    0.72
    imony
    0.70
    ispers
    0.69
     answering
    0.69
    Act Density 0.022%

    No Known Activations