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

    Neuronpedia

    INDEX
    Explanations

    phrases that begin with the word "what."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aina
    -0.16
    ntax
    -0.16
    anki
    -0.15
    inqu
    -0.15
    assy
    -0.15
    ÙĬا
    -0.14
    ephir
    -0.14
    ExecutionContext
    -0.14
    æķµ
    -0.14
    swer
    -0.14
    POSITIVE LOGITS
    urre
    0.17
     sake
    0.16
    bes
    0.15
    avin
    0.15
    kl
    0.14
    اÙĨد
    0.14
    anos
    0.14
    berger
    0.14
    esson
    0.14
     disarm
    0.14
    Act Density 0.061%

    No Known Activations