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

    Neuronpedia

    INDEX
    Explanations

    the auxiliary verb "have" in various forms and contexts

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

    would have

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     crois
    -0.37
     chrétien
    -0.36
     viven
    -0.33
     vicenda
    -0.31
    ets
    -0.30
     چیست
    -0.29
    ówek
    -0.28
    setCurrent
    -0.27
     espagnol
    -0.27
     révé
    -0.27
    POSITIVE LOGITS
    iſche
    0.78
    iſchen
    0.77
    ſelben
    0.75
    ########.
    0.75
    niſſe
    0.74
     مرئيه
    0.74
     would
    0.72
     MainAxisSize
    0.71
    GEBURTSDATUM
    0.70
    ſſung
    0.69
    Act Density 0.020%

    No Known Activations