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

    Neuronpedia

    INDEX
    Explanations

    phrases introducing questions or prompts to engage the reader

    oai_token-act-pair · gpt-3.5-turbo

    the word "have" in various contexts, indicating questions or statements about possession or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etter
    -0.63
    uit
    -0.61
    arter
    -0.59
    etting
    -0.59
    peak
    -0.58
    apo
    -0.57
    hesis
    -0.56
    dark
    -0.55
    stration
    -0.55
     deception
    -0.55
    POSITIVE LOGITS
     been
    1.24
    been
    1.14
     Been
    1.06
     undergone
    0.93
     gotten
    0.92
    gotten
    0.88
    kell
    0.84
     begun
    0.77
    asts
    0.77
     entertained
    0.76
    Act Density 0.165%

    No Known Activations