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

    Neuronpedia

    INDEX
    Explanations

    The main thing this neuron is looking for is the word "author."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of authors and their works

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Nicaragua
    -0.69
    tone
    -0.68
    ll
    -0.68
    EMS
    -0.67
     Poles
    -0.66
     Buenos
    -0.65
     USDA
    -0.64
     Ukrainians
    -0.64
    Gun
    -0.62
     Bots
    -0.62
    POSITIVE LOGITS
    itatively
    1.57
    itar
    1.21
    itarian
    1.20
    itative
    1.13
    essee
    0.99
    hip
    0.98
    uscript
    0.84
    itism
    0.84
    ãĥĦ
    0.84
    sonian
    0.84
    Act Density 0.030%

    No Known Activations