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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating varying degrees of value, quality, or efficiency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ëįĺ
    -0.16
     Yates
    -0.16
    ductive
    -0.15
    eye
    -0.15
    .elementAt
    -0.14
    ÑĢоÑĩ
    -0.14
    еÑĩение
    -0.14
     شدÙĨ
    -0.14
    ilder
    -0.14
    lessness
    -0.14
    POSITIVE LOGITS
    istically
    0.38
    aneously
    0.36
    ensively
    0.35
    lessly
    0.35
    iously
    0.34
    grily
    0.34
    atically
    0.33
    -wise
    0.33
    ynchronously
    0.33
    ishly
    0.33
    Act Density 0.403%

    No Known Activations