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

    Neuronpedia

    INDEX
    Explanations

    action verbs and terms related to processes or activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ey
    -0.15
     Gibbs
    -0.15
    azen
    -0.15
    ména
    -0.15
    adele
    -0.14
    riba
    -0.14
     Desired
    -0.14
    quire
    -0.14
    ness
    -0.14
    ISTS
    -0.14
    POSITIVE LOGITS
    ed
    0.32
    edBy
    0.28
    edata
    0.19
    stered
    0.18
    ized
    0.16
    edException
    0.16
    äºĨ
    0.16
    edith
    0.16
    edn
    0.15
    edar
    0.15
    Act Density 0.124%

    No Known Activations