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

    Neuronpedia

    INDEX
    Explanations

    names of people, especially repeated names

    oai_token-act-pair · gpt-3.5-turbo

    terms related to specific locations or significant entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Iv
    -1.02
     ANGEL
    -0.89
     Kik
    -0.88
     IG
    -0.86
     Atkinson
    -0.85
     Eggs
    -0.82
     Io
    -0.82
     Lump
    -0.78
     Angel
    -0.78
     eggs
    -0.78
    POSITIVE LOGITS
    re
    1.76
    RE
    1.44
    reb
    1.38
    rem
    1.32
    res
    1.30
    arre
    1.26
    rea
    1.21
    rey
    1.19
    rer
    1.19
    rete
    1.17
    Act Density 0.196%

    No Known Activations