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

    Neuronpedia

    INDEX
    Explanations

    variations of certain verbs in different grammatical forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ourt
    -0.16
    eyle
    -0.16
    apia
    -0.15
    eer
    -0.15
     Pere
    -0.14
    ร
    -0.14
    ÙijÙIJ
    -0.14
    c
    -0.13
    lse
    -0.13
    arget
    -0.13
    POSITIVE LOGITS
    chen
    0.23
    zsche
    0.18
    legg
    0.17
    лим
    0.16
    lein
    0.15
    ög
    0.15
    liche
    0.15
    cheng
    0.15
    addock
    0.15
    -mf
    0.15
    Act Density 0.074%

    No Known Activations