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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "all" and variations of it, indicating a focus on inclusivity or comprehensiveness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    er
    -0.53
     antaranya
    -0.49
    Deserializer
    -0.46
    бие
    -0.46
     {
    -0.45
    Ge
    -0.44
    ेश
    -0.44
     darse
    -0.43
    Millan
    -0.43
    lyn
    -0.43
    POSITIVE LOGITS
    ^(@)
    0.96
    olesale
    0.93
     모든
    0.88
     всички
    0.88
    atever
    0.87
    あらゆる
    0.86
     $_"
    0.85
     sämtliche
    0.84
     leaſt
    0.84
    Semua
    0.84
    Act Density 0.359%

    No Known Activations