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

    Neuronpedia

    INDEX
    Explanations

    mentions of respect in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    upa
    -0.17
    antry
    -0.15
    dk
    -0.15
    ystore
    -0.14
    kits
    -0.14
     fix
    -0.14
    presso
    -0.14
    erals
    -0.14
    igkeit
    -0.14
    airo
    -0.14
    POSITIVE LOGITS
    ively
    0.35
    ably
    0.30
    uously
    0.20
    ability
    0.20
    ually
    0.19
    ully
    0.18
    ive
    0.18
    abilité
    0.17
    uous
    0.17
    orary
    0.17
    Act Density 0.027%

    No Known Activations