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

    Neuronpedia

    INDEX
    Explanations

    the word "bot" with varying degrees of emphasis

    oai_token-act-pair · gpt-3.5-turbo

    references to artificial intelligence or robotic entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    journal
    -0.71
     Difference
    -0.65
    egal
    -0.63
    uncture
    -0.60
     Koen
    -0.60
    UME
    -0.59
     ACTION
    -0.59
     Situation
    -0.58
     Scheme
    -0.58
    eways
    -0.58
    POSITIVE LOGITS
    anical
    1.16
    anooga
    1.02
    cham
    1.01
    anic
    0.97
    bot
    0.90
    opia
    0.90
    olean
    0.90
    ertodd
    0.89
    ãĤ´ãĥ³
    0.89
    ically
    0.88
    Act Density 0.006%

    No Known Activations