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

    Neuronpedia

    INDEX
    Explanations

    the presence of verbs and personal pronouns within a narrative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    discussing slavery and race

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     SEDS
    -0.39
     RSSSF
    -0.36
     whatnot
    -0.36
    awaiter
    -0.36
     rând
    -0.35
     învă
    -0.34
    jstor
    -0.34
     dafs
    -0.34
    MAXN
    -0.33
    IsContent
    -0.33
    POSITIVE LOGITS
    WriteTagHelper
    0.66
    帖最后由
    0.66
     ,
    0.56
     Normdatei
    0.54
     Infórmanos
    0.52
     يتيمه
    0.50
    SharedCtor
    0.50
    исленность
    0.50
     كومونز
    0.50
    InjectAttribute
    0.50
    Act Density 0.071%

    No Known Activations