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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating personal possession or ownership

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    s
    -0.19
     unanim
    -0.16
    '
    -0.16
    tero
    -0.16
    çļĦ人
    -0.15
     yourselves
    -0.14
    ueva
    -0.14
    (es
    -0.14
     aftermath
    -0.13
    inia
    -0.13
    POSITIVE LOGITS
    rtle
    0.32
    anmar
    0.29
    opic
    0.27
    riad
    0.27
    croft
    0.26
    ri
    0.26
    opia
    0.25
     husband
    0.22
    rrha
    0.22
    rna
    0.21
    Act Density 0.197%

    No Known Activations