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

    Neuronpedia

    INDEX
    Explanations

    references to book or game covers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Intervention
    -0.16
    nou
    -0.15
     Freed
    -0.15
     Hampton
    -0.15
    egan
    -0.15
     Compare
    -0.15
     intervention
    -0.15
    Compare
    -0.14
    down
    -0.14
     down
    -0.14
    POSITIVE LOGITS
    AndView
    0.15
     Garr
    0.15
    à¥įतà¤ķ
    0.14
    yles
    0.14
    kie
    0.14
    .ObjectMeta
    0.14
    acman
    0.13
    alu
    0.13
    rud
    0.13
    oproject
    0.13
    Act Density 0.222%

    No Known Activations