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

    Neuronpedia

    INDEX
    Explanations

    words or phrases related to categories or types

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate types or categories of things, often with qualifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sbm
    -0.84
    aspers
    -0.75
    aughs
    -0.72
     Days
    -0.71
    Phones
    -0.70
    endas
    -0.68
    itness
    -0.68
    ecause
    -0.67
    arks
    -0.67
     sts
    -0.66
    POSITIVE LOGITS
     whatsoever
    0.77
     meaningful
    0.76
     altercation
    0.72
    place
    0.71
     semblance
    0.70
    icipated
    0.70
     intermediary
    0.70
     imaginable
    0.68
     uptick
    0.68
     conceivable
    0.67
    Act Density 0.046%

    No Known Activations