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

    Neuronpedia

    INDEX
    Explanations

    occurrences of fractions or ratios in numerical form

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     decken
    -0.39
     beschlossen
    -0.38
    PhysRevLett
    -0.38
    grano
    -0.37
    Abit
    -0.37
     reichen
    -0.37
    帖最后由
    -0.37
     verfügen
    -0.36
     Pairs
    -0.35
    入った
    -0.35
    POSITIVE LOGITS
    SharedDtor
    0.57
    half
    0.56
     half
    0.56
     Biôgrafia
    0.55
     betweenstory
    0.52
    Half
    0.52
     ¼
    0.49
     quarter
    0.49
    ⅙
    0.49
    %</
    0.48
    Act Density 0.282%

    No Known Activations