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

    Neuronpedia

    INDEX
    Explanations

    instances of conjunctions and transitional phrases in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ighth
    -0.15
    å¬
    -0.14
    crew
    -0.14
    quam
    -0.14
    à¹Ĥà¸Ķ
    -0.14
     tit
    -0.14
    olo
    -0.13
    hir
    -0.13
    oro
    -0.13
    adow
    -0.13
    POSITIVE LOGITS
     etc
    0.17
    OKIE
    0.16
    etc
    0.16
    sto
    0.15
    arsing
    0.14
    ynos
    0.14
    они
    0.14
    485
    0.13
    PCP
    0.13
    lient
    0.13
    Act Density 0.158%

    No Known Activations