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

    Neuronpedia

    INDEX
    Explanations

    expressions of intention or determination

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

    intend to do

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     citazioni
    -0.42
    ⠀⠀⠀⠀⠀⠀⠀⠀
    -0.41
    JSONException
    -0.40
     élimin
    -0.40
    ötzlich
    -0.40
     Boyer
    -0.39
     apareció
    -0.39
     Sucher
    -0.38
    zieher
    -0.38
    Unexpected
    -0.38
    POSITIVE LOGITS
     intend
    1.28
     intends
    1.14
     intending
    0.93
    intend
    0.89
     Intent
    0.64
     intende
    0.59
     intents
    0.59
    intent
    0.59
     Utf
    0.59
    Intent
    0.57
    Act Density 0.009%

    No Known Activations