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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating benefits or improvements

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

    not only but also

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tarko
    -0.39
     bisog
    -0.39
     MONT
    -0.38
     télévision
    -0.37
     määrä
    -0.36
     Florida
    -0.36
     Leigh
    -0.36
     suun
    -0.35
     pétrole
    -0.35
     Le
    -0.34
    POSITIVE LOGITS
     autorytatywna
    0.69
    хьтан
    0.63
     Signalez
    0.57
    MLLoader
    0.57
     Exactos
    0.57
    MigrationBuilder
    0.57
     <>",
    0.56
    ьажоргаш
    0.55
     Wikimedijinoj
    0.55
     Administrativna
    0.55
    Act Density 0.052%

    No Known Activations