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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "who" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    égor
    -0.16
    .scalablytyped
    -0.16
    illos
    -0.16
    elic
    -0.16
     nett
    -0.15
     æĸ
    -0.15
    niej
    -0.14
    ayette
    -0.14
    swick
    -0.14
    æݧ
    -0.14
    POSITIVE LOGITS
    soever
    0.22
    곡
    0.20
    abouts
    0.19
    arton
    0.18
    ver
    0.17
    302
    0.16
    craft
    0.15
    729
    0.15
     unst
    0.15
     else
    0.15
    Act Density 0.084%

    No Known Activations