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

    Neuronpedia

    INDEX
    Explanations

    verbs that indicate the possibility or capability of an action or outcome

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

    these followed by verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    GEBURTSDATUM
    -0.73
    Personendaten
    -0.44
     ویکی‌پدیای
    -0.43
    thums
    -0.42
    новништво
    -0.41
     lèvres
    -0.40
    帖最后由
    -0.40
     actionPerformed
    -0.39
     kollu
    -0.37
    conductivity
    -0.36
    POSITIVE LOGITS
     cherchés
    0.56
     lesquels
    0.54
     amelyek
    0.52
     those
    0.52
     Theſe
    0.51
     ones
    0.51
     autorytatywna
    0.48
     THOSE
    0.48
     replacements
    0.47
     celles
    0.47
    Act Density 0.033%

    No Known Activations