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

    Neuronpedia

    INDEX
    Explanations

    phrases introducing examples or clarifications

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "say" indicating reported speech or quotation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xtap
    -0.78
    leeve
    -0.78
    aughs
    -0.72
    OGR
    -0.71
    taboola
    -0.66
    wald
    -0.65
    obal
    -0.65
    folios
    -0.65
     Compensation
    -0.64
    onut
    -0.64
    POSITIVE LOGITS
    lihood
    0.85
    ings
    0.83
     goodbye
    0.80
     hello
    0.73
    ership
    0.71
    parts
    0.67
    lly
    0.65
    ies
    0.64
    volent
    0.64
    abouts
    0.62
    Act Density 0.026%

    No Known Activations