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

    Neuronpedia

    INDEX
    Explanations

    the concept of focus in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     hans
    -0.17
    utan
    -0.16
    IMS
    -0.16
     Holmes
    -0.16
    oner
    -0.15
    ectors
    -0.15
     vin
    -0.15
    antine
    -0.14
    anson
    -0.14
    tl
    -0.14
    POSITIVE LOGITS
    cus
    0.21
    ussed
    0.20
    usses
    0.17
    λια
    0.17
    uss
    0.16
    selling
    0.15
    cing
    0.15
    ingular
    0.15
    ilon
    0.14
     Mitch
    0.14
    Act Density 0.008%

    No Known Activations