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

    Neuronpedia

    INDEX
    Explanations

    negative integers or references to negative values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     nahilalakip
    -0.75
    ContextHolder
    -0.65
    th
    -0.64
    TagHelper
    -0.62
     NgModule
    -0.59
    MockBean
    -0.55
     <<<<<<<<<<<<<<
    -0.54
    LEncoder
    -0.52
     Référence
    -0.52
    argout
    -0.52
    POSITIVE LOGITS
    year
    0.68
    ounce
    0.62
    hecta
    0.60
    carat
    0.59
    foot
    0.58
    kilometer
    0.58
    acre
    0.57
    minute
    0.56
     to
    0.55
    YEAR
    0.55
    Act Density 0.290%

    No Known Activations