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

    Neuronpedia

    INDEX
    Explanations

    quantitative terms and references to units of measurement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pi
    -0.59
    ')['
    -0.54
    hast
    -0.53
    なぜか
    -0.51
     nogal
    -0.51
    complexContent
    -0.50
    UMBIA
    -0.49
    }$​
    -0.48
    assertNotNull
    -0.48
    offsetof
    -0.46
    POSITIVE LOGITS
    WriteTagHelper
    0.75
     '{@
    0.69
     NSCoder
    0.66
    IsContent
    0.65
    SourceChecksum
    0.63
     MutableLiveData
    0.63
     sekal
    0.62
    djangoproject
    0.61
    pædia
    0.61
     woord
    0.61
    Act Density 0.186%

    No Known Activations