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

    Neuronpedia

    INDEX
    Explanations

    pronouns and verbs indicating actions or states of being

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anka
    -0.15
    ocks
    -0.15
     must
    -0.15
     doesn
    -0.14
    chos
    -0.14
    oner
    -0.14
     immedi
    -0.14
    escaping
    -0.14
    ãĥ¼ãĥª
    -0.13
    ãĥªãĥ¼ãĤº
    -0.13
    POSITIVE LOGITS
     near
    0.31
     ne
    0.29
     prepares
    0.28
     prepare
    0.28
     prepared
    0.27
    near
    0.27
     gears
    0.24
    prepared
    0.24
    await
    0.23
     gear
    0.23
    Act Density 0.169%

    No Known Activations