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

    Neuronpedia

    INDEX
    Explanations

    phrases related to intention or intended actions

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

    "intend" or "intended"

    np_acts-logits-general · gemini-2.0-flash

    intend to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    expandindo
    -0.94
     poffe
    -0.83
     Efq
    -0.76
     becauſe
    -0.76
     AssemblyCompany
    -0.74
    tagHelper
    -0.73
     يتيمه
    -0.72
     Jefus
    -0.71
    :✨
    -0.71
     themſelves
    -0.69
    POSITIVE LOGITS
     intended
    0.91
     intent
    0.81
     Intended
    0.80
    Intent
    0.77
    intent
    0.77
     intends
    0.77
    Intended
    0.76
    intended
    0.74
     Intent
    0.73
     intend
    0.70
    Act Density 0.142%

    No Known Activations