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

    Neuronpedia

    INDEX
    Explanations

    references to legal terms or processes

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the substring "pr"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    liner
    -0.70
    wolves
    -0.68
     EntityItem
    -0.68
    querque
    -0.66
     Hunts
    -0.66
    croft
    -0.65
    bleacher
    -0.64
     Druid
    -0.64
     Cheong
    -0.63
    brainer
    -0.63
    POSITIVE LOGITS
    udence
    1.15
    atche
    0.96
    imate
    0.94
    ima
    0.93
    ayer
    0.90
    icing
    0.90
    asion
    0.90
    acy
    0.89
    agin
    0.88
    imes
    0.88
    Act Density 0.006%

    No Known Activations