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

    Neuronpedia

    INDEX
    Explanations

    phrases or clauses related to "what" or "that" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÌĨ
    -0.15
     Vera
    -0.15
    illion
    -0.15
    士
    -0.15
    ÃŃsto
    -0.14
     Hole
    -0.14
    holes
    -0.14
    tracted
    -0.14
     Sir
    -0.14
    uner
    -0.14
    POSITIVE LOGITS
     Kushner
    0.17
    arius
    0.14
    .gs
    0.14
    away
    0.14
    aves
    0.14
    adr
    0.14
     Brace
    0.14
    лÑıн
    0.13
    é¡Ķ
    0.13
    akt
    0.13
    Act Density 0.049%

    No Known Activations