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

    Neuronpedia

    INDEX
    Explanations

    comparisons between quantities or characteristics

    oai_token-act-pair · gpt-3.5-turbo

    comparative statements regarding families and socioeconomic status

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    >)
    -0.82
     âĢ¦"
    -0.71
     »
    -0.70
    SHARE
    -0.70
     pic
    -0.69
     WEEK
    -0.69
     BUS
    -0.66
    "))
    -0.65
     */
    -0.63
    raits
    -0.63
    POSITIVE LOGITS
    .[
    2.79
    ,[
    2.78
    ".[
    2.59
    ."[
    2.36
    ).[
    2.32
    :[
    2.29
    [
    2.12
    )[
    1.84
    "[
    1.70
    ][
    1.65
    Act Density 0.486%

    No Known Activations