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

    Neuronpedia

    INDEX
    Explanations

    words related to coding and programming

    oai_token-act-pair · gpt-3.5-turbo

    instances of references to people or items associated with metrics or data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Kik
    -0.91
     Ich
    -0.87
     Katz
    -0.81
    bats
    -0.78
     Kabul
    -0.76
     346
    -0.76
    ilk
    -0.75
    aces
    -0.73
     Sachs
    -0.72
     Axis
    -0.72
    POSITIVE LOGITS
    re
    1.44
    RE
    1.39
    Re
    1.25
     RE
    1.20
    rez
    1.15
    reb
    1.15
     Reaper
    1.12
     Re
    1.11
    rev
    1.09
    rem
    1.08
    Act Density 0.321%

    No Known Activations