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

    Neuronpedia

    INDEX
    Explanations

    verbs indicating states or conditions, particularly in different tenses

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

    no noun was verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     zwar
    -0.49
     GenerationType
    -0.48
    جغرافيا
    -0.47
     Diſ
    -0.47
     beginnetje
    -0.46
    already
    -0.45
    adaptiveStyles
    -0.44
     createContext
    -0.43
    cshtml
    -0.43
    Already
    -0.43
    POSITIVE LOGITS
     ever
    1.41
     EVER
    1.08
     jemals
    1.06
     Ever
    0.85
    ever
    0.85
     whatsoever
    0.82
    Ever
    0.77
     ooit
    0.76
    EVER
    0.70
     jamais
    0.69
    Act Density 0.046%

    No Known Activations