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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to activism and social issues

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

    Follows words indicating uncertainty or hope

    np_acts-logits-general · gemini-2.0-flash

    crossed that

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .”
    -0.75
    !”
    -0.70
     quæ
    -0.70
     …”
    -0.67
     ſtate
    -0.66
    !!”
    -0.66
    TestingModule
    -0.65
     appunto
    -0.64
    ."
    -0.63
     perſon
    -0.63
    POSITIVE LOGITS
     nahilalakip
    0.87
     disambiguazione
    0.84
     سكانية
    0.80
    twimg
    0.76
     tartalomajánló
    0.76
    脚注の使い方
    0.69
     Administrativna
    0.66
    tagHelperRunner
    0.63
     lenker
    0.63
    TemporalType
    0.61
    Act Density 0.381%

    No Known Activations