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

    Neuronpedia

    INDEX
    Explanations

    terms related to numerical values and mathematical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .*")]
    -0.70
    +#+#
    -0.64
    Попис
    -0.58
     ostavi
    -0.56
     للمعارف
    -0.56
    ştır
    -0.54
     @"/
    -0.54
    Datuak
    -0.53
     Datenschutzer
    -0.52
    béco
    -0.51
    POSITIVE LOGITS
     كومونز
    0.71
    AddTagHelper
    0.54
     setw
    0.51
    rimin
    0.50
    hematical
    0.50
    isinstance
    0.49
    öpf
    0.48
    strictEqual
    0.47
    olume
    0.47
    atguigu
    0.47
    Act Density 0.924%

    No Known Activations