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

    Neuronpedia

    INDEX
    Explanations

    mentions of past individuals or positions in positions of power

    oai_token-act-pair · gpt-3.5-turbo

    references to government officials and positions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    dash after "then"

    Explanation Uploaded by User

    - after time adverb especially "then"

    Explanation Uploaded by User
    New Auto-Interp
    Negative Logits
    kson
    -0.80
    zsche
    -0.76
     Dickinson
    -0.75
     ROCK
    -0.74
     DRAG
    -0.70
     "$:/
    -0.65
     Steal
    -0.64
     Tune
    -0.64
     dances
    -0.62
     âĿ
    -0.62
    POSITIVE LOGITS
    president
    0.89
    develop
    0.86
    const
    0.86
    cand
    0.86
    timer
    0.86
    vict
    0.84
    prem
    0.81
    chance
    0.81
    tim
    0.80
    director
    0.79
    Act Density 0.039%

    No Known Activations