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

    Neuronpedia

    INDEX
    Explanations

    words that indicate location and types of adjectives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ensis
    -0.15
     olun
    -0.15
    ιά
    -0.15
    ìķ½
    -0.14
    asley
    -0.14
     Palin
    -0.14
     Brake
    -0.14
     Williams
    -0.13
    esini
    -0.13
    ocab
    -0.13
    POSITIVE LOGITS
    669
    0.17
    ammo
    0.15
    ãĤ¤ãĤº
    0.15
     Ripple
    0.14
    CAS
    0.14
    .Transactional
    0.14
    buster
    0.14
    pile
    0.14
    topl
    0.14
    River
    0.13
    Act Density 0.092%

    No Known Activations