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

    Neuronpedia

    INDEX
    Explanations

    the word "Be" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    recht
    -0.15
    rik
    -0.15
    ar
    -0.15
    so
    -0.15
    .sg
    -0.15
    rib
    -0.15
    ri
    -0.14
    .chapter
    -0.14
    bidden
    -0.14
    ww
    -0.14
    POSITIVE LOGITS
    atrix
    0.28
    auf
    0.22
    arded
    0.21
    ardless
    0.21
    heading
    0.20
     sure
    0.20
    autiful
    0.19
    ause
    0.19
    (Be
    0.18
    aucoup
    0.18
    Act Density 0.031%

    No Known Activations