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

    Neuronpedia

    INDEX
    Explanations

    words related to specialization or unique expertise

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    äºĨ
    -0.18
    tracts
    -0.17
    INED
    -0.16
    ged
    -0.16
    held
    -0.16
    опол
    -0.16
    nech
    -0.15
    aged
    -0.15
    ined
    -0.15
    433
    -0.15
    POSITIVE LOGITS
    ism
    0.22
    isms
    0.21
    alties
    0.16
    ices
    0.16
    ISM
    0.16
    al
    0.15
     CID
    0.14
    itsu
    0.14
    izer
    0.14
    CID
    0.14
    Act Density 0.005%

    No Known Activations