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

    Neuronpedia

    INDEX
    Explanations

    phrases related to quantities and data references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Clik
    -0.67
     getContext
    -0.63
    TagHelper
    -0.62
     agak
    -0.60
    drage
    -0.58
    withIdentifier
    -0.57
     happiest
    -0.57
    somewhat
    -0.56
     rústico
    -0.55
    withstanding
    -0.54
    POSITIVE LOGITS
     numerous
    1.28
     countless
    1.25
    Numerous
    1.22
     innumerable
    1.19
     myriad
    1.14
     Numerous
    1.14
     multitude
    1.10
     many
    1.08
     zahlreiche
    1.02
     dozens
    1.01
    Act Density 0.201%

    No Known Activations