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

    Neuronpedia

    INDEX
    Explanations

    negative values or indications of loss

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ValueStyle
    -1.28
     CreateTagHelper
    -1.21
     متعلقه
    -1.18
     مشين
    -1.13
     nahilalakip
    -1.09
    UnusedPrivate
    -1.09
     myſelf
    -1.06
    expandindo
    -1.03
     Anſ
    -1.02
     Roskov
    -1.02
    POSITIVE LOGITS
     
    0.83
     '
    0.60
    ↵
    0.59
    ↵↵
    0.58
     [
    0.57
     $\
    0.57
     "
    0.55
     General
    0.51
    ()[
    0.51
     general
    0.50
    Act Density 0.046%

    No Known Activations