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

    Neuronpedia

    INDEX
    Explanations

    mentions of individuals in roles related to authority, such as officials and spokespersons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     transfieras
    -0.67
     protoimpl
    -0.61
     surla
    -0.61
     resourceCulture
    -0.60
     createSlice
    -0.59
     Италијани
    -0.59
     مشين
    -0.58
    󠁢
    -0.58
     ddelweddau
    -0.57
    transQ
    -0.56
    POSITIVE LOGITS
     said
    0.55
     explained
    0.44
     explains
    0.41
     says
    0.41
     وقال
    0.41
    said
    0.39
     trem
    0.38
    StringLen
    0.35
     told
    0.35
     sti
    0.34
    Act Density 0.154%

    No Known Activations