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

    Neuronpedia

    INDEX
    Explanations

    references to workshops, events, and educational courses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     forces
    -0.16
    umba
    -0.15
     Weed
    -0.15
    hr
    -0.15
     Friedman
    -0.15
    some
    -0.15
    se
    -0.15
     Lamb
    -0.14
    acy
    -0.14
     Cent
    -0.14
    POSITIVE LOGITS
    ubern
    0.16
    çį
    0.15
    Tube
    0.15
    lijke
    0.15
    gary
    0.15
    สำà¹Ģร
    0.15
    ácil
    0.14
    çIJ
    0.14
    hoc
    0.14
    WebKit
    0.14
    Act Density 0.338%

    No Known Activations