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

    Neuronpedia

    INDEX
    Explanations

    phrases or words of people taking action or calling on others to take action

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ^(@)
    -0.90
    CppMethod
    -0.85
    neder
    -0.82
    "])
    -0.76
     Reſ
    -0.74
     Efq
    -0.74
     greateſt
    -0.71
    gameserver
    -0.69
     doubtnut
    -0.69
     ―――――
    -0.69
    POSITIVE LOGITS
     to
    0.54
    asker
    0.51
    ask
    0.47
     către
    0.45
    Einzelnachweise
    0.45
     Communauté
    0.45
     ask
    0.44
    目で
    0.44
     Brust
    0.43
     asker
    0.42
    Act Density 2.675%

    No Known Activations