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

    Neuronpedia

    INDEX
    Explanations

    linguistic variations and transformations of verbs and their grammatical forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    stellung
    -0.23
     saw
    -0.17
     ate
    -0.17
    werk
    -0.17
     gave
    -0.17
     drew
    -0.16
     Nose
    -0.16
    ernal
    -0.15
    itou
    -0.15
     took
    -0.15
    POSITIVE LOGITS
    ichtet
    0.27
    unden
    0.22
    etzt
    0.21
    ählt
    0.20
    zeichnet
    0.20
    ellt
    0.19
    agt
    0.18
    nom
    0.18
    issen
    0.18
    legt
    0.18
    Act Density 0.019%

    No Known Activations