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

    Neuronpedia

    INDEX
    Explanations

    mentions of academic citations and references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ensburg
    -0.16
    itors
    -0.15
     Trails
    -0.14
     Soros
    -0.14
    @student
    -0.14
     Stra
    -0.14
    arious
    -0.14
    iteur
    -0.13
    atos
    -0.13
    iture
    -0.13
    POSITIVE LOGITS
     Coleman
    0.16
    ypi
    0.16
     perform
    0.14
     Чи
    0.14
     Carrier
    0.14
    \d
    0.14
     Cummings
    0.14
    utherford
    0.14
    ahas
    0.13
    erval
    0.13
    Act Density 0.012%

    No Known Activations