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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "for."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ob
    -0.15
     доÑģÑĤ
    -0.15
     Consolid
    -0.14
    ast
    -0.14
     UNUSED
    -0.14
    Nb
    -0.14
     Lub
    -0.13
     Socorro
    -0.13
     Await
    -0.13
    voy
    -0.13
    POSITIVE LOGITS
    pollo
    0.18
    aggio
    0.15
    anger
    0.15
    ptr
    0.15
    izr
    0.15
    rames
    0.15
    ToLocal
    0.15
    lys
    0.14
    ully
    0.14
    lé
    0.14
    Act Density 0.049%

    No Known Activations