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

    Neuronpedia

    INDEX
    Explanations

    references to the term "her" or variations thereof

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ingly
    -0.17
    olet
    -0.16
    nya
    -0.15
    yt
    -0.15
    amas
    -0.15
    ra
    -0.14
    relude
    -0.14
    OTT
    -0.14
    yny
    -0.14
    ns
    -0.14
    POSITIVE LOGITS
    itage
    0.30
    editary
    0.30
     Majesty
    0.26
    bst
    0.24
    metic
    0.24
    ders
    0.23
    mit
    0.23
    ding
    0.22
    etical
    0.22
    acle
    0.21
    Act Density 0.032%

    No Known Activations