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

    Neuronpedia

    INDEX
    Explanations

    future tense verbs and expressions of intention or expectation

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

    future actions or intentions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     would
    -0.84
    Would
    -0.79
     Would
    -0.78
     WOULD
    -0.71
    would
    -0.70
     &=&
    -0.61
     zou
    -0.61
    &=&\
    -0.57
    &=&
    -0.56
     wouldn
    -0.54
    POSITIVE LOGITS
     Bewußt
    0.53
    ientôt
    0.49
     ayudará
    0.43
     Mulai
    0.43
     duquel
    0.41
     Füße
    0.41
     telefónica
    0.41
     temprana
    0.41
     verrez
    0.39
     aguj
    0.39
    Act Density 0.211%

    No Known Activations