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

    Neuronpedia

    INDEX
    Explanations

    instances where the text discusses or invites sharing personal information or experiences

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "share" and its variations, highlighting communication and sharing information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    paio
    -0.74
    sil
    -0.66
    isman
    -0.62
    heid
    -0.62
    berus
    -0.61
    HS
    -0.60
     desper
    -0.60
    equipped
    -0.60
    abiding
    -0.60
    isma
    -0.60
    POSITIVE LOGITS
    cro
    1.01
    hare
    0.77
    holders
    0.76
    Tweet
    0.73
    holder
    0.70
    onym
    0.69
    URL
    0.68
    ivity
    0.67
     anecdotes
    0.66
    alogue
    0.66
    Act Density 0.024%

    No Known Activations