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

    Neuronpedia

    INDEX
    Explanations

    references to internal systems or processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ioc
    -0.17
    ois
    -0.15
    nish
    -0.14
    اÙģت
    -0.14
    -shaped
    -0.14
    redient
    -0.14
    iability
    -0.14
    ableView
    -0.14
    alyzer
    -0.14
    bai
    -0.14
    POSITIVE LOGITS
    /Internal
    0.40
    /internal
    0.33
    .Internal
    0.24
    izado
    0.23
    ized
    0.22
    /ext
    0.21
    halb
    0.21
    (internal
    0.21
     Affairs
    0.20
    most
    0.20
    Act Density 0.030%

    No Known Activations