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

    Neuronpedia

    INDEX
    Explanations

    words related to narcotics or drug culture

    oai_token-act-pair · gpt-3.5-turbo

    common prefixes or syllables that appear frequently in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Accountability
    -0.83
     Plum
    -0.81
     Pend
    -0.77
     Parish
    -0.73
    ioxide
    -0.72
    éĹĺ
    -0.72
     Station
    -0.72
     Redd
    -0.71
    ingham
    -0.70
    edIn
    -0.69
    POSITIVE LOGITS
    ocular
    0.79
    ls
    0.79
    uary
    0.75
    umin
    0.74
    uture
    0.73
    ourage
    0.72
    DNA
    0.71
     lang
    0.69
    ented
    0.67
    wn
    0.67
    Act Density 0.066%

    No Known Activations