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

    Neuronpedia

    INDEX
    Explanations

    pronouns and modal verbs indicating capability or possibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iez
    -0.17
    ie
    -0.15
     Pant
    -0.14
     Vers
    -0.14
     Att
    -0.14
     att
    -0.14
     Mon
    -0.14
    cano
    -0.14
    orny
    -0.14
     cou
    -0.14
    POSITIVE LOGITS
    опол
    0.16
    解
    0.15
    æĪ·
    0.15
    antino
    0.15
     speculation
    0.14
     Fault
    0.14
    ogi
    0.14
    skyt
    0.14
    Å¡ka
    0.14
    -mf
    0.14
    Act Density 0.003%

    No Known Activations