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

    Neuronpedia

    INDEX
    Explanations

    phrases and terms related to conclusions and summarizing outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    걸
    -0.16
    ened
    -0.16
    load
    -0.15
     걸
    -0.15
    ych
    -0.15
    balls
    -0.15
    Ñijл
    -0.15
    etics
    -0.15
    aged
    -0.14
    ÙĪراÙĨ
    -0.14
    POSITIVE LOGITS
    aires
    0.23
    aire
    0.21
     Reached
    0.20
    naire
    0.20
     reached
    0.17
     remarks
    0.17
    swith
    0.16
    èIJ¥
    0.15
    ãģ¨ãģĵãĤį
    0.15
    isser
    0.15
    Act Density 0.015%

    No Known Activations