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

    Neuronpedia

    INDEX
    Explanations

    references to rules and eligibility criteria for participation in programs or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sticks
    -0.17
    lette
    -0.15
    unma
    -0.15
     stiff
    -0.14
    oser
    -0.14
    alte
    -0.14
    rial
    -0.13
    rips
    -0.13
    ekl
    -0.13
    authorized
    -0.13
    POSITIVE LOGITS
    elli
    0.17
    owe
    0.16
    usted
    0.16
    igm
    0.15
    RAP
    0.14
    erge
    0.13
    enci
    0.13
    ench
    0.13
    ectomy
    0.13
     unlikely
    0.13
    Act Density 0.274%

    No Known Activations