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

    Neuronpedia

    INDEX
    Explanations

    editor's notes

    oai_token-act-pair · gpt-3.5-turbo

    possessive pronouns and references to editorial notes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abouts
    -0.82
    Downloadha
    -0.74
    yip
    -0.74
    illy
    -0.71
    ĪĴ
    -0.69
    ril
    -0.66
    sters
    -0.64
    rill
    -0.62
     beds
    -0.62
     plaus
    -0.61
    POSITIVE LOGITS
    Publisher
    0.93
     Picks
    0.90
     Editorial
    0.76
    lishing
    0.74
     editorial
    0.72
    lisher
    0.72
    ature
    0.71
    Edge
    0.70
    Journal
    0.69
     Dragonbound
    0.68
    Act Density 0.087%

    No Known Activations