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

    Neuronpedia

    INDEX
    Explanations

    infinitive verbs and phrases related to intentions or desires

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

    actions after "to"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Grind
    -0.49
     trier
    -0.49
    TRAILING
    -0.49
    ngOnInit
    -0.48
    LookAnd
    -0.47
     Gag
    -0.47
     Taj
    -0.47
     arg
    -0.46
    agre
    -0.45
     Gage
    -0.45
    POSITIVE LOGITS
    Véxase
    0.50
     quieren
    0.46
     Economía
    0.46
     Biaya
    0.46
    ########.
    0.44
     Tujuan
    0.43
     Infór
    0.43
     fiscales
    0.42
     Inscrivez
    0.41
     istället
    0.41
    Act Density 0.036%

    No Known Activations