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

    Neuronpedia

    INDEX
    Explanations

    words related to longer passages of text with a specific focus on potential conversation or narrative

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ngth
    -0.96
    gerald
    -0.87
    strom
    -0.81
    viks
    -0.79
     Pwr
    -0.79
    ĸļ
    -0.78
    icone
    -0.77
    xp
    -0.72
    thouse
    -0.71
    kefeller
    -0.71
    POSITIVE LOGITS
     topic
    1.15
     impending
    1.15
     upcoming
    1.09
     topics
    1.08
     specifics
    0.92
     looming
    0.90
     motivations
    0.88
     imminent
    0.86
     methodology
    0.84
     behalf
    0.84
    Act Density 0.551%

    No Known Activations