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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "yet."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     yet
    -0.32
    yet
    -0.31
     Yet
    -0.25
    Yet
    -0.23
    -yellow
    -0.17
     już
    -0.17
     déjÃł
    -0.16
    缮åīį
    -0.15
    aggio
    -0.15
    Å¡tÃŃ
    -0.14
    POSITIVE LOGITS
    tings
    0.21
    fulness
    0.19
    ting
    0.19
     fully
    0.17
    fully
    0.17
    tt
    0.17
    å®ļçļĦ
    0.16
    ters
    0.16
    ty
    0.16
    ournaments
    0.15
    Act Density 0.018%

    No Known Activations