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

    Neuronpedia

    INDEX
    Explanations

    references to community efforts and their impacts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    chwitz
    -0.15
    анÑģов
    -0.15
    OLON
    -0.14
    uslim
    -0.14
    arin
    -0.14
     Matters
    -0.14
    üst
    -0.13
    /stdc
    -0.13
    annis
    -0.13
    olk
    -0.13
    POSITIVE LOGITS
     strong
    0.25
     proper
    0.22
     investments
    0.21
     good
    0.21
     having
    0.20
     intervention
    0.20
    good
    0.19
    having
    0.18
    strong
    0.18
     close
    0.18
    Act Density 0.256%

    No Known Activations