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

    Neuronpedia

    INDEX
    Explanations

    numerical data and references to specific items or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Fleming
    -0.16
    IX
    -0.15
     unh
    -0.15
    EDIUM
    -0.14
    sta
    -0.14
    ix
    -0.14
     Haut
    -0.14
    VIDEO
    -0.14
     gr
    -0.13
    .Module
    -0.13
    POSITIVE LOGITS
     Bench
    0.17
    raÄį
    0.16
    oogle
    0.15
    gist
    0.15
    umer
    0.15
    mps
    0.15
    CompleteListener
    0.15
     bench
    0.15
     benches
    0.14
    zÄħd
    0.14
    Act Density 0.173%

    No Known Activations