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

    Neuronpedia

    INDEX
    Explanations

    expressions that convey intent or desire followed by the infinitive form of verbs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     daudz
    -0.83
    vats
    -0.62
    baix
    -0.62
    FORMAN
    -0.61
     Alen
    -0.58
    splitlines
    -0.58
    fiés
    -0.57
    martre
    -0.57
     cobra
    -0.56
     Dat
    -0.56
    POSITIVE LOGITS
     estimés
    1.01
     wanna
    0.88
    wanna
    0.85
    Wanna
    0.84
     Wanna
    0.83
     querem
    0.82
     WIC
    0.81
     entend
    0.79
     quiero
    0.76
     Gonna
    0.75
    Act Density 0.106%

    No Known Activations