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

    Neuronpedia

    INDEX
    Explanations

    quotes or statements attributed to individuals

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "quoted."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ¯¯¯¯¯¯¯¯
    -0.80
    ¯¯¯¯
    -0.74
     Arbor
    -0.72
    ggles
    -0.71
    estate
    -0.71
    ét
    -0.71
    perm
    -0.70
    appers
    -0.69
    venge
    -0.69
    vals
    -0.68
    POSITIVE LOGITS
     snippets
    0.88
     quotes
    0.87
     quoted
    0.87
     quoting
    0.82
     excerpts
    0.79
     phrases
    0.77
     sources
    0.73
    Bloomberg
    0.70
     unnamed
    0.69
     quote
    0.65
    Act Density 0.014%

    No Known Activations