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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of mutation or changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aug
    -0.16
    haled
    -0.16
    issen
    -0.15
    onte
    -0.15
    858
    -0.15
    OrUpdate
    -0.15
    ós
    -0.14
    isters
    -0.14
    es
    -0.14
    UD
    -0.14
    POSITIVE LOGITS
    iple
    0.22
    agen
    0.20
     mutual
    0.20
     Mut
    0.20
    mut
    0.20
    ually
    0.20
    ual
    0.19
     Mutual
    0.18
    tl
    0.17
     mut
    0.17
    Act Density 0.008%

    No Known Activations