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

    Neuronpedia

    INDEX
    Explanations

    pronouns and verbs related to communication

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals in the context of communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ikan
    -0.64
    ibal
    -0.62
    arious
    -0.60
    hift
    -0.60
    akia
    -0.59
    xtap
    -0.58
    inf
    -0.58
    ierre
    -0.58
    ilde
    -0.57
     Category
    -0.56
    POSITIVE LOGITS
    DERR
    0.92
    selves
    0.86
     goodbye
    0.85
    ij士
    0.75
     orally
    0.74
    terday
    0.68
     daughters
    0.67
     farewell
    0.67
     privately
    0.67
    self
    0.65
    Act Density 0.110%

    No Known Activations